Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks271 from public data
- Plan-and-Write: Towards Better Automatic Storytelling515
Experiments show that with explicit storyline planning, the generated stories are more diverse, coherent, and on topic than those generated without creating a full plan, according to both automatic and human evaluations.
- Natural Language Inference by Tree-Based Convolution and Heuristic Matching372
This model, a tree-based convolutional neural network (TBCNN) captures sentence-level semantics; then heuristic matching layers like concatenation, element-wise product/difference combine the information in individual sentences.
- Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System352
This paper proposes a retrieval-based conversation system with the deep learning-to-respond schema through a deep neural network framework driven by web data and demonstrates significant performance improvement against a series of standard and state-of-art baselines for conversational purposes.
- How Transferable are Neural Networks in NLP Applications?305
In this paper, systematic case studies are conducted and an illuminating picture is provided on the transferability of neural networks in NLP.
- Multi-view Response Selection for Human-Computer Conversation233
Experimental results on a public corpus for context-sensitive response selection demonstrate the effectiveness of the proposed multi-view model, which significantly outperforms other single-view baselines.
- RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems228
RUBER is proposed, a Referenced metric and Unreferenced metrics Blended Evaluation Routine, which evaluates a reply by taking into consideration both a groundtruth reply and a query (previous user-issued utterance).
- CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling216
This paper proposes CGMH, a novel approach using Metropolis-Hastings sampling for constrained sentence generation that allows complicated constraints such as the occurrence of multiple keywords in the target sentences, which cannot be handled in traditional RNN-based approaches.
- Citation count prediction211
This paper has implemented a system which takes a series of features of a particular publication as input and produces as output the estimated citation counts of that article after a given time period and considers several regression models to formulate the learning process and evaluate their performance based on the coefficient of determination (R-square).
- Knowledge-Grounded Dialogue Generation with Pre-trained Language Models206
Empirical results indicate that the proposed response generation defined by a pre-trained language model with a knowledge selection module and an unsupervised approach to jointly optimizing knowledge selection and response generation with unlabeled dialogues can significantly outperform state-of-the-art methods in both automatic evaluation and human judgment.
- Evolutionary timeline summarization205
A novel framework for the web mining problem named Evolutionary Timeline Summarization (ETS), which aims to return the evolution trajectory along the timeline, consisting of individual but correlated summaries of each date, emphasizing relevance, coverage, coherence and cross-date diversity.
- Get The Point of My Utterance! Learning Towards Effective Responses with Multi-Head Attention Mechanism165
A novel Multi-Head Attention Mechanism (MHAM) for generative dialog systems, which aims at capturing multiple semantic aspects from the user utterance is proposed, and a regularizer is formulated to force different attention heads to concentrate on certain aspects.
- OVERCOMING CATASTROPHIC FORGETTING FOR CONTINUAL LEARNING VIA MODEL ADAPTATION155
This paper proposes a very different approach, called Parameter Generation and Model Adaptation (PGMA), to dealing with the problem of catastrophic forgetting in standard neural network architectures.
- Multi-Representation Fusion Network for Multi-Turn Response Selection in Retrieval-Based Chatbots142
This work proposes a multi-representation fusion network where the representations can be fused into matching at an early stage, at an intermediate stage, or at the last stage, and demonstrates the effect of each representation to matching, which sheds light on how to select them in practical systems.
- How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models133
This paper conducts an empirical study to compare various models and investigate the effect of context information in dialog systems, and proposes a variant that explicitly weights context vectors by context-query relevance, outperforming the other baselines.
- One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues129
Evaluation results on three benchmark data sets indicate that IoI can significantly outperform state-of-the-art methods in terms of various matching metrics and unveil how the depth of interaction affects the performance of IoI.
- To better stand on the shoulder of giants125
This work learns to identify potentially influential literature via Future Influence Prediction (FIP), which aims to estimate the future influence of literature, and applies the learned model to the application of bibliography recommendation and obtains prominent performance improvement in terms of Mean Average Precision (MAP).
- An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems112
Experimental results show that a novel ensemble of retrieval-based and generation-based conversation system outperforms each single module by a large margin.
- i, poet: automatic poetry composition through recurrent neural networks with iterative polishing schema110
This paper forms the poetry composition task as a natural language generation problem using recurrent neural networks, and proposes a new generative model with a polishing schema, and outputs a refined poem composition.
- Tweet Recommendation with Graph Co-Ranking108
A graph-theoretic model for tweet recommendation that presents users with items they may have an interest in and can be parametrized to take into account user preferences, the popularity of tweets and their authors, and diversity.
- VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles96
A Dual-Interaction-based Multimodal Summarizer (DIMS), consisting of a dual interaction module and multimodal generator that handles the semantic relationship between news text and video from a high level.
- Timeline Generation through Evolutionary Trans-Temporal Summarization96
Evaluation results in ROUGE metrics indicate the effectiveness of the proposed approach based on trans-temporal information, and a novel combination of inter-date and intra-date sentence dependencies is presented.
- Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix94
It is shown that the dynamic transition matrix can effectively characterize the noise in the training data built by distant supervision and can be effectively trained using a novel curriculum learning based method without any direct supervision about the noise.
- "Chitty-Chitty-Chat Bot": Deep Learning for Conversational AI93
This paper focuses on the survey of non-task-oriented chit-chat bots, which can converse seamlessly and appropriately with humans, playing the role of a chat companion.
- Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems92
This paper proposes an implicit content-introducing method which incorporates additional information into the Seq2Seq model in a flexible way and fuse the general decoding and the auxiliary cue word information through the proposed hierarchical gated fusion unit.
- Product-Aware Answer Generation in E-Commerce Question-Answering90
The task of product-aware answer generation, which tends to generate an accurate and complete answer from large-scale unlabeled e-commerce reviews and product attributes is proposed, which is composed of three components: a question-aware review representation module, a key-value memory network encoding attributes, and a recurrent neural network as a sequence generator.
- CharacterChat: Learning towards Conversational AI with Personalized Social Support83
CharacterChat is presented, a comprehensive S2Conv system, which includes a conversational model driven by personas and memories, along with an interpersonal matching plugin model that dispatches the optimal supporters from the MBTI-1024 Bank for individuals with specific personas.
- 81
- 81
- Abstractive Text Summarization by Incorporating Reader Comments80
The task of reader-aware abstractive summary generation is proposed, which utilizes the reader comments to help the model produce better summary about the main aspect.
- 78
- 78
- Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues76
This paper proposes learning a context-response matching model with auxiliary self-supervised tasks designed for the dialogue data based on pre-trained language models and jointly train the PLM-based response selection model with these auxiliary tasks in a multi-task manner.
- Interview Choice Reveals Your Preference on the Market72
A novel matching network with preference modeled is proposed to explore the latent preference given the history of all interviewed candidates for a job posting and thehistory of all job applications for a particular talent to improve job-resume matching on the job market.
- Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation70
A relation-aware multi-document encoder that relates one document to another according to their content dependency in a relation graph that generates an abstractive related work from the given multiple scientific papers in the same research area is proposed.
- Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training67
Experimental results on a large poetry corpus confirm the validity and effectiveness of the proposed conditional variational autoencoder with adversarial training for classical Chinese poem generation, where its automatic and human evaluation scores outperform existing models.
- DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy64
DetermLR is proposed, a novel perspective that rethinks the reasoning process as an evolution from indeterminacy to determinacy and achieves higher accuracy with fewer reasoning steps, highlighting its superior efficiency and effectiveness in solving logical reasoning tasks.
- Towards Effective and Interpretable Person-Job Fitting62
The proposed IPJF model leverages deep interactive representation learning to automatically learn the interdependence between a resume and job requirements without relying on a clear list of job seeker's abilities, and deploys the optimizing problem as a learning to rank problem.
- Summarize What You Are Interested In: An Optimization Framework for Interactive Personalized Summarization59
This work investigates an important and challenging problem in summary generation, i.e., Interactive Personalized Summarization (IPS), which generates summaries in an interactive and personalized manner and develops experimental systems to compare 5 rival algorithms on 4 different datasets.
- Scale Up Event Extraction Learning via Automatic Training Data Generation57
This work develops an automatic approach for generating training data for event extraction that allows to scale up event extraction training instances from thousands to hundreds of thousands, and it does this at a much lower cost than a manual approach.
- Unsupervised link prediction using aggregative statistics on heterogeneous social networks57
A novel unsupervised framework to solve the problem of link prediction with aggregative statistics problem, including two main components: a three-layer factor graph model and three types of potential functions; and a ranked-margin learning and inference algorithm.
- Predictive Adversarial Learning from Positive and Unlabeled Data56
Evaluation of the proposed novel Predictive Adversarial Networks (PAN) based on GAN shows that PAN outperforms state-of-the-art PU learning methods and also a direct adaptation of GAN for PU learning.
- The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News54
This study introduces a novel multi-agent system with LLMs named TruEDebate (TED) to enhance the interpretability and effectiveness of fake news detection and releases code to support Information systems that use structured debate within responsible information systems for improved decision-making.
- 53
- Semi-supervised Text Style Transfer: Cross Projection in Latent Space53
A semi-supervised text style transfer model that combines the small-scale parallel data with the large-scale nonparallel data is proposed and a projection function between the latent space of different styles is introduced.
- 53
- RetroGraph52
This work proposes a graph-based search policy that eliminates the redundant explorations of any intermediate molecules in the searching process and adopts a graph neural network to guide the search over graphs.
- Learning towards conversational AI: A survey50
This paper divides existing prevailing frameworks for a dialogue model into three categories and analyzes the trend of development for open-domain dialogue and summarizes the goal of an open-domain dialogue system in two aspects, informative and controllable.
- Meaningful Answer Generation of E-Commerce Question-Answering50
A novel generative neural model, called the Meaningful Product Answer Generator (MPAG), which alleviates the safe answer problem by taking product reviews, product attributes, and a prototype answer into consideration and achieves state-of-the-art performance in terms of both automatic metrics and human evaluations.
- Learning towards Abstractive Timeline Summarization49
This paper proposes a memory-based timeline summarization model (MTS), which tends to concisely paraphrase the information in the time-stamped events and achieves the state-of-the-art performance in terms of both automatic and human evaluations.
- From Standard Summarization to New Tasks and Beyond: Summarization with Manifold Information48
This paper focuses on the survey of these new summarization tasks and approaches in the real-world application of text summarization algorithms.
- Joint Learning of Response Ranking and Next Utterance Suggestion in Human-Computer Conversation System48
A novel Dual-LSTM Chain Model is proposed to couple response ranking and next utterance suggestion simultaneously simultaneously and it is assumed that the new conversation mode is more proactive and keeps user engaging.
- Are Training Samples Correlated? Learning to Generate Dialogue Responses with Multiple References47
Experimental results show that the proposed model can effectively improve the quality of response and outperform existing neural dialogue models on both automatic and human evaluations.
- Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders46
Experimental results on a large-scale real-world dataset confirm the superiority of the proposed model for generating informative and personalized responses, where both automatic and human evaluations outperform state-of-the-art models.
- A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots44
A document-grounded matching network for response selection that can power a knowledge-aware retrieval-based chatbot system that can significantly improve upon state-of-the-art methods and at the same time enjoys good interpretability.
- Marrying Up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding44
Novel methods to exploit the rich expressiveness of REs at different levels within a NN are developed, showing that the combination significantly enhances the learning effectiveness when a small number of training examples are available.
- Causality-Guided Multi-Memory Interaction Network for Multivariate Stock Price Movement Prediction42
The proposed Causality-guided Multi-memory Interaction Network (CMIN), a novel end-to-end deep neural network for stock movement prediction which, for the first time, models the multi-modality between financial text data and causality-enhanced stock correlations to achieve higher prediction accuracy.
- Iterative Document Representation Learning Towards Summarization with Polishing42
This paper introduces Iterative Text Summarization (ITS), an iteration-based model for supervised extractive text summarization inspired by the observation that it is often necessary for a human to read an article multiple times in order to fully understand and summarize its contents.
- Insufficient Data Can Also Rock! Learning to Converse Using Smaller Data with Augmentation41
A novel generative model is proposed to augment existing data, where the conditional variational autoencoder is employed as the generator to output more training data with diversified expressions to improve the performance of neural dialogue models on the condition of insufficient data.
- Breaking the barriers of data scarcity in drug–target affinity prediction40
The proposed Semi-Supervised Multi-task training (SSM)-DTA framework addresses the data limitation challenge in DTA prediction and yields promising results, paving the way for more efficient and accurate drug discovery processes.
- Target-aware Abstractive Related Work Generation with Contrastive Learning40
An abstractive target-aware related work generator (TAG) is proposed, which models the relationships between reference papers and the target paper with target-centered attention mechanisms and brings substantial improvements over several strong baselines in terms of automatic and tailored human evaluations.
- Dialogue Session Segmentation by Embedding-Enhanced TextTiling39
This paper aims to demonstrate the efforts towards in-situ applicability of EMMARM, the objective of which is to provide real-time information about concrete mechanical properties such as E-modulus and compressive strength.
- 38
- "Shall I Be Your Chat Companion?": Towards an Online Human-Computer Conversation System38
This paper introduces a chat companion system, which is a practical conversation system between human and computer as a real application, and investigates the performance between effectiveness and efficiency for the proposed methods.
- Timeline generation with social attention37
This work captures social attention by learning users' collective interests in the form of word distributions from Twitter, which are subsequently incorporated into a unified framework for timeline summary generation, and sheds light on the feasibility of incorporating social attention into traditional text mining tasks.
- Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks36
This paper proposes an algorithm that can customize a unique dialogue model for each task in the few-shot setting and shows that this method outperforms all the baselines in terms of task consistency, response quality, and diversity.
- Coupled Context Modeling for Deep Chit-Chat36
A novel context modeling framework with end-to-end neural networks for human-computer conversational systems that will search for appropriate responses, conduct relevance ranking using contexts information, and then output the highly relevant result.
- Dialogue History Matters! Personalized Response Selection in Multi-Turn Retrieval-Based Chatbots35
This work incorporates user-specific dialogue history into the response selection and proposes a personalized hybrid matching network (PHMN), which significantly outperforms several strong models by combining personalized attention, wording behaviors, and hybrid representation learning.
- Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems35
Empirical studies indicate that compared with the widely used random sampling strategy, although the first two strategies lead to performance drop, the latter two ones can bring consistent improvement to the performance of all the models on both benchmarks.
- Who Is Speaking to Whom? Learning to Identify Utterance Addressee in Multi-Party Conversations33
This paper introduces a novel who-to-whom (W2W) model which models users and utterances in the session jointly in an interactive way and demonstrates that the model outperforms baselines with consistent improvements.
- Recognizing Entailment and Contradiction by Tree-based Convolution33
Experimental results on a large dataset verify the rationale of using TBCNN as the sentencelevel model; leveraging additional heuristics like element-wise product/difference further improves the accuracy.
- Deep Chit-Chat32
This tutorial starts from a summary of recent achievement made by both academia and industry on chatbots, and performs a thorough and systematic introduction to state-of-the-art methods for open domain conversation modeling including both retrieval-based methods and generation-based methods.
- Deep Chit-Chat: Deep Learning for ChatBots32
This tutorial starts from a summary of recent achievement made by both academia and industry on chatbots, and performs a thorough and systematic introduction to state-of-the-art methods for open domain conversation modeling including both retrieval-based methods and generation-based methods.
- Modeling discourse cohesion for discourse parsing via memory network32
This paper proposes a new transition-based discourse parser that makes use of memory networks to take discourse cohesion into account, and the automatically captured discourse cohesion benefits discourse parsing, especially for long span scenarios.
- Selection and Generation: Learning towards Multi-Product Advertisement Post Generation31
A novel end-to-end model named S-MG Net is proposed to generate the advertisement (AD) post and achieves impressive performance in terms of both automatic metrics as well as human evaluations.
- How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing31
Extensive experiments conducted on a large-scale real-world text summarization dataset show that PESG achieves the state-of-the-art performance in terms of both automatic metrics and human evaluations.
- Towards a Neural Conversation Model With Diversity Net Using Determinantal Point Processes30
A novel framework which organically combines seq2seq model with Determinantal Point Processes is proposed, which achieves high quality in generated reply and significantly improves the diversity among them.
- Opportunities or risks to reduce labor in crowdsourcing translation? characterizing cost versus quality via a pagerank-HITS hybrid model30
This paper proposes a graphbased PageRank-HITS Hybrid model to distinguish authoritative workers from unreliable ones, and demonstrates the algorithm will keep the performance while reduce work force and hence cut cost.
- Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models29
A novel analytic method aimed at decomposing the outputs of the MLP into components understandable by humans is proposed and observed a universal anti-overconfidence mechanism in the final layer of models, which suppresses correct predictions.
- 29
- Enhancing Surgical Nursing Student Performance: Comparative Study of Simulation-Based Learning and Problem-Based Learning28
SBL and PBL improve nurses’ core competence, satisfaction, and self-confidence, and improvements are needed in fidelity, objectives, information, and students’ expectations.
- A Survey on Response Selection for Retrieval-based Dialogues28
A comprehensive survey of recent advances in response selection for retrieval-based dialogues and summarizes some recent advances on the research of response selection, including incorporation with extra knowledge and exploration on more effective model learning.
- Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems28
To learn a robust matching model from noisy training data, a general co-teaching framework with three specific teaching strategies that cover both teaching with loss functions and teaching with data curriculum is proposed.
- Learning to Converse with Noisy Data: Generation with Calibration28
This paper proposes a generation with calibration framework, that allows high- quality data to have more influences on the generation model and reduces the effect of noisy data.
- An Analysis and Mitigation of the Reversal Curse27
The first-ever study of how the reversal curse happens in LLMs is undertaken, revealing that the reversal curse can stem from the specific training objectives, which become particularly evident in the widespread use of next-token prediction within most causal language models.
- Conversational Recommendation via Hierarchical Information Modeling27
This paper proposes Hierarchical Information-aware Conversational Recommender (HICR) to model the two types of hierarchical information to boost the performance of CRS.
- Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems27
A multi-turn Response Selection Model that can Detect the relevant parts of the Context and Knowledge collection (RSM-DCK) is proposed that achieves better performance than the existing methods, and can effectively detect the relevant context and knowledge for response selection.
- MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions26
A Memory-based Self-evolution mechanism, which summarizes the experience from successful execution, is developed, to improve the performance of MobileSteward, a self-evolving multi-agent framework which integrates multiple app-oriented StaffAgents coordinated by a centralized StewardAgent.
- Chinese Couplet Generation with Neural Network Structures26
This paper forms the task as a natural language generation problem using neural network structures, and incorporates the attention mechanism and polishing schema into the encoding-decoding process to satisfy special characteristics of couplets.
- Stick to the Facts: Learning towards a Fidelity-oriented E-Commerce Product Description Generation25
This work proposes a model named Fidelity-oriented Product Description Generator (FPDG), which takes the entity label of each word into account, since the product attribute information is always conveyed by entity words.
- 25
- Follow the Timeline! Generating an Abstractive and Extractive Timeline Summary in Chronological Order24
The Unified Timeline Summarizer is proposed, which can generate abstractive and extractive timeline summaries in time order and achieves state-of-the-art performance in terms of both automatic and human evaluations.
- 24
- 23
- Smarter Response with Proactive Suggestion: A New Generative Neural Conversation Paradigm23
This paper proposes a new paradigm for neural generative conversations: smarter response with a suggestion is provided given the query and proposes a novel integrated model to handle both the response generation and the suggestion generation.
- On the Abstractiveness of Neural Document Summarization23
A pure copy system was implemented, which achieved comparable results as abstractive summarizers while being far more computationally efficient.
- Are Two Heads Better than One? Crowdsourced Translation via a Two-Step Collaboration of Non-Professional Translators and Editors22
This paper develops graphbased ranking models that automatically select the best output from multiple redundant versions of translations and edits, and improves translation quality closer to professionals.
- Excavation of diagnostic biomarkers and construction of prognostic model for clear cell renal cell carcinoma based on urine proteomics21
The application of urine proteomics to explore diagnostic biomarkers and to construct prognostic models of renal clear cell carcinoma is of certain clinical value and can significantly predict the prognosis of ccRCC patients.
- Deep Learning for Dialogue Systems: Chit-Chat and Beyond21
This monograph presents a taxonomy of the various dimensions of fair information access and survey the literature to date on this new and rapidly-growing topic.
- The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement21
A Disentanglement-based Attractive Headline Generator (DAHG) that generates headline which captures the attractive content following the attractive style and takes the polished document as input to generate headline under the guidance of the attractive Style.
- 21
- EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator20
A novel application named EZInterviewer is proposed, which aims to learn from the online interview data and provides mock interview services to the job seekers and achieves promising results to generate mock interviews.
- Semi-Offline Reinforcement Learning for Optimized Text Generation19
This work proposes semi-offline RL, a novel paradigm that smoothly transits from offline to online settings, balances exploration capability and training cost, and provides a theoretical foundation for comparing different RL settings.
- Enriching Cold Start Personalized Language Model Using Social Network Information19
A generalized framework to enrich the personalized language models for cold start users, whose mixture weights are derived from prior knowledge and heuris- tics to identify the most appropriate weights.
- 18
- Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering18
LLMQA is proposed, a generalized framework that formulates the ODQA process into three basic steps: query expansion, document selection, and answer generation, combining the superiority of both retrieval-based and generation-based evidence.
- Dialogue Summarization with Static-Dynamic Structure Fusion Graph18
A Static-Dynamic graph-based Dialogue Summarization model (SDDS), which fuses prior knowledge from human expertise and adaptively learns the graph structure in an end-to-end learning fashion is proposed and the results verify the superiority of SDDS.
- Learning to Respond with Your Favorite Stickers18
This article proposes a Preference Enhanced Sticker Response Selector (PESRS) model, which learns the short-term and long-term dependency between all interaction results by a fusion network and dynamically fuses the user preference representation into the final sticker selection prediction.
- What If Bots Feel Moods?18
An emotion-aware transition network is proposed to model the dynamic emotional flow and enhance context-response matching in retrieval-based dialogue systems with learnt intrinsic emotion features through a multi-task learning framework and is applied to a real IoT application.
- EnsembleGAN18
This paper proposes ensembleGAN, an adversarial learning framework for enhancing a retrieval-generation ensemble model in open-domain conversation scenario that consists of a language-model-like generator, a ranker generator, and one ranker discriminator.
- Joint Emoji Classification and Embedding Learning18
A matching architecture using deep neural networks to jointly learn emoji embeddings and make classification is proposed, which demonstrates the effectiveness of the proposed approach better than traditional softmax methods in terms of p@1, p@5 and MRR evaluation metrics.
- Guess What You Will Cite: Personalized Citation Recommendation Based on Users’ Preference18
This paper considers the citation recommendation as a content based analysis combined with personalization, using users’ publication or citation history as users' profile and conduct to a personalized citation recommendation, which results in an 27.65% improvement of the performance in terms of MAP and 31.67% improvement in recall@10 compared with state-of-art models for citation recommendation problem.
- GETMusic: Generating Music Tracks with a Unified Representation and Diffusion Framework17
This paper introduces a framework known as GETMusic, with ``GET'' standing for ``GEnerate music Tracks'' and a novel music representation ``GETScore'' and a diffusion model ``GETDiff'' that empowers GETMusic to generate music with any arbitrary source-target track combinations.
- 16
- 16
- MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruiting15
MockLLM, a novel framework to generate and evaluate mock interview interactions that outperforms existing methods in matching accuracy, scalability, and adaptability across job domains, highlighting its potential to advance candidate assessment and online recruitment.
- Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension15
This paper proposes a joint framework that unifies these two tasks, sharing the same encoder to extract the common and task-invariant features with different decoders to learn task-specific features, and augments the Transformer architecture with a memory updater, designed to selectively store and update the history dialog information so as to support downstream tasks.
- Enhancing the Open-Domain Dialogue Evaluation in Latent Space15
This paper proposes a self-supervised setting to obtain a smooth latent space that can both capture discourse-level context information and implicitly model more references in latent space and demonstrates the superiority of this method for open-domain dialogue evaluation.
- How does Truth Evolve into Fake News? An Empirical Study of Fake News Evolution15
The Fake News Evolution (FNE) dataset is presented: a new dataset tracking the fake news evolution process, composed of 950 paired data that observe the features during the evolution and they are the disinformation techniques, text similarity, top 10 keywords, classification accuracy, parts of speech, and sentiment properties.
- Context-to-Session Matching: Utilizing Whole Session for Response Selection in Information-Seeking Dialogue Systems15
The response and its context as a whole session is considered and the task of matching the query's context with the sessions is explored and the proposed context-to-session method outperforms the strong baselines significantly.
- Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search14
Symbolic Graph Ranker (SGR) is proposed, which aims to take advantage of both text-based and graph-based approaches by leveraging the power of recent Large Language Models (LLMs) and introduces a set of self-supervised symbolic learning tasks to enable LLMs to capture the topological information from coarse-grained to fine-grained.
- Bridging the Space Gap: Unifying Geometry Knowledge Graph Embedding with Optimal Transport14
UniGE stands out as a novel KGE method that seamlessly integrates KGE in both Euclidean and hyperbolic geometric spaces, and an embedding alignment method and fusion strategy, which harnesses optimal transport techniques and the Wasserstein barycenter method are introduced.
- Decouple knowledge from parameters for plug-and-play language modeling13
PlugLM is introduced, a pre-training model with differentiable plug-in memory (DPM) that can de-couple the knowledge storage from model parameters with an editable and scalable key-value memory and leverage knowledge in an explainable manner by knowledge retrieval in the DPM.
- Towards Personalized Review Summarization by Modeling Historical Reviews from Customer and Product Separately13
The Heterogeneous Historical Review aware Review Summarization Model (HHRRS) is proposed which separately models the two types of historical reviews with the rating information by a graph reasoning module with a contrastive loss.
- ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation13
A novel dialogue generation framework named ProphetChat is proposed that utilizes the simulated dialogue futures in the inference phase to enhance response generation and demonstrates that ProphetChat can generate better responses over strong baselines, which validates the advantages of incorporating the simulatedDialogue futures.
- Multilingual COVID-QA: Learning towards Global Information Sharing via Web Question Answering in Multiple Languages13
A novel framework which incorporates (unsupervised) translation alignment to learn as pseudo-parallel data is proposed and the effectiveness of the proposed approach compared against a series of competitive baselines is demonstrated.
- Be Aware of the Hot Zone: A Warning System of Hazard Area Prediction to Intervene Novel Coronavirus COVID-19 Outbreak13
A system predicting hazard areas on the basis of confirmed infection cases with location information and achieving promising overall performance in terms of precision, recall, accuracy, F1 score, and AUC is built.
- One "Ruler" for All Languages: Multi-Lingual Dialogue Evaluation with Adversarial Multi-Task Learning13
Experiments show that the adversarial multi-task neural metric (ADVMT) achieves a high correlation with human annotation, which yields better performance than monolingual ones and various existing metrics.
- Diversifying Neural Conversation Model with Maximal Marginal Relevance.13
This paper proposes the MMR-BS decoding method, which incorporates MMR into the beam search (BS) process of seq2seq, and shows that the proposed model achieves the best performance among other comparison methods.
- Ranking news events by influence decay and information fusion for media and users13
This work proposes five strategies which only exploit media focus to decide news influence impact and provides three strategies to combine user attention with media focus and takes four types of interaction between user attention and media focus into consideration.
- GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Framework12
A unified representation and diffusion framework named GETMusic, which includes a novel music representation named GETScore, and a diffusion model named GETDiff, which provides high-quality results across diverse combinations and surpasses prior works proposed for some specific combinations.
- Learning Disentangled Representation via Domain Adaptation for Dialogue Summarization12
A disentangled representation method to reduce the deviation between data in different domains, where the input data is disentangling into domain-invariant and domain-specific representations, and two novel reconstruction strategies, namely backtracked and cross-track reconstructions, are proposed.
- 12
- 12
- Tackling the Achilles Heel of Social Networks12
This paper formulate a socialized factor graph model, which utilizes both the textual correlations between document pairs and the socialized augmentation networks behind the documents, such as user relationships and social interactions, to tackle the Achilles Heel of social networks by smoothing the language model via influence propagation.
- The role of comfort, personality, and intention in smartwatch usage during sleep11
It is found that the appearance and movement dimensions of comfort significantly influence users’ intention to wear the smartwatch during sleep, while other dimensions like pressure, harm, attachment, and perceived change do not show significant effects.
- Treatment for essential tremor: a systematic review and Bayesian Model-based Network Meta-analysis of RCTs11
DBS is effective for medication-resistant ET and ranks first in relative efficacy, though the NMA lacks safety data for DBS, and further large-scale, head-to-head RCTs are needed.
- SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents11
SpokenWOZ is introduced, a large-scale speech-text dataset for spoken TOD, which consists of 8 domains, 203k turns, 5.7k dialogues and 249 hours of audios from human-to-human spoken conversations and presents cross-turn slot and reasoning slot detection as new challenges based on the spoken linguistic phenomena.
- Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study11
By running comprehensive comparisons, this paper quantitatively compare the ability of several representative neural models to organize sentences from a bag of words under three typical scenarios, and summarizes some empirical findings and challenges, which can shed light on future research on this line of work.
- Event Recognition from News Webpages through Latent Ingredients Extraction11
Two novel event recognition models based on LIs extraction are presented and exploit a set of useful features consisting of context similarity, distance restriction, entity influence from thesaurus and temporal proximity.
- HeteroQA10
This work proposes a question-aware heterogeneous graph transformer to incorporate the MIS in the user community to automatically generate the answer in Community Question Answering.
- 10
- Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues10
The model can handle the relation of neighboring elements, phrasal pattern, and long-range dependencies during the representation and make a more accurate prediction through multiple layers of interactions between the context–response pair.
- 9
- 9
- Your Career Path Matters in Person-Job Fit9
This paper proposes a new approach to person-job fit that characterizes the hidden preference derived from the job seeker's career path and proves that understanding the career path enables us to provide more appropriate career suggestions to job seekers.
- StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generation9
Experimental results show that the proposed framework StyleChat outperforms all the baselines and helps to break the style boundary of LLMs, which has been carefully constructed with rigorous human-led quality control.
- 9
- Sixth International Joint Conference on Natural Language Processing9
This paper deals with the fast bootstrapping of Grapheme-to-Phoneme (G2P) conversion system, which is a key module for both automatic speech recognition (ASR), and text- to-speech synthesis (TTS).
- Efficient phrase querying with flat position index9
This paper proposes a novel cache sensitive look-up table (CSLT), which is much faster than existing search algorithms and can reduce the index size and speed up phrase querying substantially, compared with traditional word-level index.
- YAYI 2: Multilingual Open-Source Large Language Models8
YAYI 2 is pre-trained from scratch on a multilingual corpus which contains 2.65 trillion tokens filtered by the pre-training data processing pipeline, and outperforms other similar sized open-source models.
- Delving into Global Dialogue Structures: Structure Planning Augmented Response Selection for Multi-turn Conversations8
A novel structure model comprising a state recognizer and a structure planner is proposed that effectively captures the flow within the utterance history and plans the trajectory of future utterances, enabling seamless integration with existing retrieval models and facilitating collaborative training.
- Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order8
A Unified Timeline Summarizer (UTS) that can generate abstractive and extractive timeline summaries in time order is proposed and achieves state-of-the-art performance in terms of both automatic and human evaluations.
- Finding the Dominant Winning Ticket in Pre-Trained Language Models8
Strikingly, it is found that a dominant winning ticket that takes up 0.05% of the parameters can already achieve satisfactory performance, indicating that the PLM is significantly reducible during fine-tuning.
- 8
- Plan-CVAE: A Planning-Based Conditional Variational Autoencoder for Story Generation8
This paper proposes a planning-based conditional variational autoencoder, namely Plan-CVAE, which first plans a keyword sequence and then generates a story based on the keyword sequence, and outperforms state-of-the-art methods on both automatic metrics and human evaluations.
- Evaluating and Enhancing the Robustness of Retrieval-Based Dialogue Systems with Adversarial Examples8
With adversarial training using the generated adversarial examples, this paper significantly improves the robustness of retrieval-based dialogue systems and provides new insights to facilitate future work on building more robust dialogue systems.
- Overview of the NLPCC 2018 Shared Task: Multi-turn Human-Computer Conversations8
An overview of multi-turn human-computer conversations at NLPCC 2018 shared task is given, which consists of two sub-tasks: conversation generation and retrieval with given context.
- Crowdsourcing for grammatical error correction8
The task of suggesting grammar and style corrections in writing is well suited to a crowdsourcing solution but is currently hindered by the difficulty of automatic quality control, so a design for quality control is proposed.
- Empathetic Response Generation with Relation-aware Commonsense Knowledge7
This work develops a chatbot that aims to recognize and empathetically respond to users' mental states and introduces a Conditional Variational Autoencoders (CVAE)-based model that utilizes relation-aware commonsense knowledge to generate responses.
- Flexible and Adaptable Summarization via Expertise Separation7
MoeSumm is proposed, a Mixture-of-Expert Summarization architecture, which utilizes a main expert for gaining the general summarization capability and deputy experts that selectively collaborate to meet specific summarization task requirements, and proposes a max-margin loss to stimulate the separation of these abilities.
- 7
- Envisioning Future from the Past: Hierarchical Duality Learning for Multi-Turn Dialogue Generation7
A hierarchical duality learning for dialogue (HDLD) is proposed to simulate this human cognitive ability, for generating high quality responses that connect both previous and follow-up dialogues, leading to the improvement in both automatic and human evaluation.
- 7
- GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval7
A GNN-encoder model is proposed in which query (passage) information is fused into passage ( query) representations via graph neural networks that are constructed by queries and their top retrieved passages to achieve both efficiency and efficacy in passage retrieval.
- 7
- Unsupervised Mitigating Gender Bias by Character Components: A Case Study of Chinese Word Embedding7
This work proposes the first Chinese Gender-neutral word Embedding model (CGE) based on Word2vec, which learns gender- neutral word embeddings without any labeled data and utilizes and emphasizes the rich feminine and masculine information contained in radicals during the training procedure to alleviate discriminative gender biases.
- A Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded Conversations7
Experimental results on two benchmarks of knowledge-grounded response selection indicate that the model can achieve comparable performance with several existing methods that rely on crowd-sourced data for training.
- 7
- 7
- Adaptively Multi-Objective Adversarial Training for Dialogue Generation7
A novel adversarial dialogue generation framework with multiple discriminators that excel in different objectives for multiple linguistic aspects, called AMPGAN, whose feasibility is proved by theoretical derivations and an adaptively adjusted sampling distribution is designed.
- Multilingual Dialogue Generation with Shared-Private Memory7
A novel multilingual dialogue system is introduced that outperforms the individually learned model with the help of the other language, where the improvement is particularly distinct when the training data is limited.
- Socialized Language Model Smoothing via Bi-directional Influence Propagation on Social Networks7
A bi-directional socialized factor graph model is formulated, which utilizes both the textual correlations between document pairs and the socialized augmentation networks behind the documents, such as user relationships and social interactions, and an effective learning algorithm is proposed to learn the proposed factors graph model with directions.
- MIN: Multi-Channel Interaction Network for Drug-Target Interaction With Protein Distillation6
The Multi-channel Interaction Network (MIN), a novel framework designed to predict DTIs through two primary components: a representation learning module and a multi-channel interaction module, surpasses other strong DTI prediction methods and offers fresh insights into the prediction of protein binding sites.
- 2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models6
2D-TPE effectively mitigates the risk of losing essential spatial information while preserving computational efficiency, thus better preserving the table structure, and is introduced as a simple yet effective positional encoding method.
- YuLan: An Open-source Large Language Model6
A three-stage pre-training method to enhance YuLan's overall capabilities and devise a curriculum-learning framework throughout across these stages, which helps LLMs learn knowledge in an easy-to-hard manner.
- Enhanced BioT5+ for Molecule-Text Translation: A Three-Stage Approach with Data Distillation, Diverse Training, and Voting Ensemble6
The enhanced BioT5+ method ranks first in the text-based molecule generation task and second in the molecule captioning task, highlighting its efficacy and robustness in translating between molecules and natural language.
- ConvNTM: Conversational Neural Topic Model6
Comprehensive experimental results demonstrate that the proposed ConvNTM achieves the best performance both in topic modeling and in typical downstream tasks within conversational research (i.e., dialogue act classification and dialogue response generation).
- Personalized Query Suggestion with Searching Dynamic Flow for Online Recruitment6
Dynamic Searching Flow Model (DSFM) is proposed, a query suggestion framework that is capable of modeling and refining user search intent progressively in recruitment scenarios by leveraging a dynamic flow mechanism.
- Personalized Chit-Chat Generation for Recommendation Using External Chat Corpora6
A method to generate personalized chit-chat for news recommendation that only requires an external chat corpus obtained from an online forum, which can be disconnected from the recommendation dataset from both the user and item (news) perspectives is proposed.
- When Less Is More: Using Less Context Information to Generate Better Utterances in Group Conversations6
It is observed that fewer contexts can lead to better performance by tackling the structure of group conversations and the model outperforms baselines.
- Tackling Sparsity, the Achilles Heel of Social Networks: Language Model Smoothing via Social Regularization6
An optimization framework with a social regularizer for smoothing the posting document language model based on social regularization is formulated and experimental results on the Twitter dataset validate the effectiveness and efficiency of the proposed model.
- SAGraph: A Large-Scale Social Graph Dataset with Comprehensive Context for Influencer Selection in Marketing5
SAraph, a novel comprehensive dataset from Weibo that captures multi-dimensional marketing campaign data across six product domains, reveals that LLM-based approaches achieve superior performance in understanding and predicting campaign success, opening new avenues for data-driven influencer marketing strategies.
- 5
- EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond5
This article presents a synergy-aware framework, i.e., EventCrab, that adeptly integrates the"lighter"frame-specific networks for dense event frames with the"heavier"point-specific networks for sparse event points, balancing accuracy and efficiency.
- 5
- SORTIE: Dependency-Aware Symbolic Reasoning for Logical Data-to-text Generation5
This work proposes a dependency-aware symbolic reasoning framework that reasons out each entity in the table description with the authors' designed table-compatible programming language and devise an entity scheduling mechanism to determine the order of programme synthesis such that the reasoning of an entity only relies on other “re-solved” entities.
- 5
- 5
- WULAI-QA: Web Understanding and Learning with AI towards Document-based Question Answering against COVID-195
This study designs a dynamic document-based question answering system, namely Web Understanding and Learning with AI (WULAI-QA), which employs feature engineering and online learning to adapt to the non-stationary environment and maintains good and steady performance.
- Empowering Conversational AI is a Trip to Mars: Progress and Future of Open Domain Human-Computer Dialogues5
An overview of progress is presented and future trends are looked at so as to shed light on possible directions towards success in conversational studies.
- BioGen: Generating Biography Summary under Table Guidance on Wikipedia5
The TaGS (Ta ble-Guided Summarization) dataset is introduced, the first large-scale biography summarization dataset with tables, and several commonly used summarization methods are benchmarked on TaGS to inspire more exciting methods.
- Translation vs. Dialogue: A Comparative Analysis of Sequence-to-Sequence Modeling5
This paper studies the sequence-to-sequence (Seq2Seq) model in the contexts of two mainstream NLP tasks as they both use the seq2seq model to investigate how the two tasks are different and how their task difference results in major differences in the behaviors of the resulting translation and dialogue generation systems.
- Semantic v.s. Positions: Utilizing Balanced Proximity in Language Model Smoothing for Information Retrieval5
A unified proximity-based framework to smooth language models, leveraging semantic and positional information simultaneously in combination, is proposed, which is to project terms to positions where they originally do not exist (i.e., zero count).
- A finegrained digestion of news webpages through Event Snippet Extraction5
A framework to digest news webpages in finer granularity: to extract event snippets from contexts to exploit rich features to detect snippet boundaries, including various semantic, syntactic and visual features.
- PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead4
This paper proposes Position-Embedding-Agnostic attention Re-weighting (PEAR), which enhances the context awareness of LLMs with zero inference overhead, while outperforming competitive baselines in accuracy and efficiency across various RAG tasks.
- 4
- 4
- 4
- 4
- Time Domain Adversarial Voice Conversion for ADD 20224
The experimental results show that the speech generation system for the first Audio Deep Synthesis Detection Challenge (ADD 2022) has adversarial ability against anti-spoofing detectors with a little compromise in audio quality and speaker similarity.
- 4
- Learning Sense Representation from Word Representation for Unsupervised Word Sense Disambiguation (Student Abstract)4
This work proposes SGM and MGM to learn sense representations for words in WordNet using the glosses and calculates the similarity between each sense of the ambiguous word and its context to select the sense with the highest similarity in the WSD task.
- Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection4
Experimental results indicate that the proposed hierarchical contextualized representations can bring significantly and consistently improvement to existing matching models for response selection.
- Improving Matching Models with Contextualized Word Representations for Multi-turn Response Selection in Retrieval-based Chatbots.4
Experimental results on two benchmark datasets indicate that the proposed contextualized word vectors can significantly and consistently improve the performance of existing matching models for response selection.
- Hierarchical Graph Summarization: Leveraging Hybrid Information through Visible and Invisible Linkage4
This paper aims to integrate three types of hierarchical linkage into traditional graph-based methods by proposing Hierarchical Graph Summarization (HGS), utilizing a hierarchical language model to measure the sentence relationships in HGS.
- 3
- Exploiting Pre-trained Models for Drug Target Affinity Prediction with Nearest Neighbors3
This work proposes kNN-DTA, a non-parametric embedding-based retrieval method adopted on a pre-trained DTA prediction model, which can extend the power of the DTA model with no or negligible cost, and introduces two neighbor aggregation ways from both embedding space and label space that are integrated into a unified framework.
- 3
- 3
- Lower Risks, Better Choices: Stock Correlation Based Portfolio Selection in Stock Markets3
RDPC is an end-to-end reinforcement learning-based transformer trained to optimize both returns and risk, with a hard attention mechanism that learns the relationship between asset pairs, imitating the powerful pairs trading strategy widely adopted by many investors.
- 3
- Query-to-Session Matching: Do NOT Forget History and Future during Response Selection for Multi-Turn Dialogue Systems3
This paper is the first work to utilize both the response's history and future in the response selection task, and the experimental results show that the proposed model outperforms existing state-of-the-art methods by a large margin.
- Will I Win Your Favor? Predicting the Success of Altruistic Requests3
This paper develops a novel request success prediction model, termed Graph-based Predictor for Request Success (GPRS), which is featured by learning the correlation between success or not and the set of features extracted in the request, together with a label propagation-based optimization mechanism.
- 3
- 2
- 2
- 2
- 2
- Multi-Response Awareness for Retrieval-Based Conversations: Respond with Diversity via Dynamic Representation Learning2
A Respond-with-Diversity model augmented by the memory module interacting with both the query utterances and multiple candidate responses is proposed, and dynamic representations for the input queries conditioned on different response candidates are obtained.
- EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble Model on Short-Text Conversation2
- Classification over Clustering: Augmenting Text Representation with Clusters Helps!2
A new text representation scheme is proposed by clustering words according to their latent semantics and composing them together to get a set of cluster vectors, which are then concatenated as the final text representation.
- Query-bag Matching with Mutual Coverage for Information-seeking Conversations in E-commerce2
A query-bag matching model is proposed which mainly utilizes the mutual coverage between query and bag and measures the degree of the content in the query mentioned by the bag, and vice verse.
- Using Lexical and Thematic Knowledge for Name Disambiguation2
A novel approach to disambiguate names based on two different types of semantic information: lexical and thematic, using translation-based language models to resolve the synonymy problem in every word match and a topic-based ranking function to capture rich thematic contexts for names.
- 2
- Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings1
EbedFilter is introduced, a simple linear transformation designed to refine text embeddings derived from LLMs directly, finding that the unembedding matrix within LLMs encodes a latent space that is actively writing frequent tokens into embedding space, thereby enhancing semantic representations.
- 1
- Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition1
HR2G-shot is proposed, a Hierarchical Relation-augmented Representation Generalization framework for FSAR, which unifies three types of relation modeling (inter-frame, inter-video, and inter-task) to learn task-specific temporal patterns from a holistic view and outperforms current top-leading FSAR methods.
- Neuroimaging pattern interactions for suicide risk in depression captured by ensemble learning over transcriptome-defined parcellation1
An ensemble learning scheme over transcriptome-defined parcellations (TDP) to explore homogeneously parcellated brain patterns and their interactions displayed higher suicide predictive performance, relative to that over the regions level, and over null model.
- Luoling: An Immersive Cross-Modal Interactive Poem Creation Factory through Multi-Agent Collaboration1
Luoling is introduced, an immersive, cross-modal interactive poem creation factory with fine-grained, controllable attributes, driven by a multi-agent collaboration system, enabling a richer, more expressive creative process.
- 1
- Adaptive semi-supervised learning from stronger augmentation transformations of discrete text information1
The novel SeqMatch method is proposed, which can automatically perceive abnormal model states caused by anomalous data obtained by text augmentations and reduce their interferences and instead leverages normal ones to improve the effectiveness of consistency regularization.
- 1
- 1
- 1
- 1
- Bioinformatics analysis of differentially expressed genes in ischemic cardiomyopathy using GEO Database1
Bioinformatics can screen out the key genes in ischemic cardiomyopathy, which is helpful to understand the treatment of drug targets in ICM patients.
- 1
- 1
- 1
- A prediction model for targeted drug resistance in renal cell carcinoma based on plasma proteomics analysis–
Four plasma proteins—chitotriosidase-1, interleukin-6 receptor (IL-6R), neuronal cell adhesion molecule (NRCAM), and ecto-5’-nucleotidase (NT5E)—were identified as significant predictors of intrinsic resistance and developed and validated a plasma protein-based nomogram to predict mRCC resistance to targeted therapy.
- –
- Conjoint analysis of single-cell sequencing and high-throughput virtual screening regarding DDR2 in osteoarthritis disease models–
This study found that ZINC000003874604, as a lead compound, had potential therapeutic activity for OA, which may help provide more drug options in the pharmaceutical market.
- –
- An Unmanned Delivery Vehicle Path-Planning Method Based on Point-Graph Joint Embedding and Dual Decoders–
Experimental results demonstrate that the proposed path-planning model, PGDD, is superior to several state-of-the-art algorithms in solving the path-planning problem of unmanned distribution vehicles.
- –
- –
- Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking–
This work presents the siamese model optimization framework, comprising a history-conditioned model and a future-aware model, and introduces the peer knowledge distillation method with a dynamic gating mechanism, allowing models to selectively incorporate contextual information.
- –
- –
- –
- –
- –
- –
- –
- On the Compositional Generalization in Versatile Open-domain Dialogue–
This work develops a sparsely activated modular network that outperforms state-of-the-art supervised approaches on 4 datasets with only 10% training data thanks to the modular architecture and multi-task learning.
- –
- –
- Boosting Variational Generative Model via Condition Enhancing and Lexical-Editing–
An Edit-CVAE (ECVAE) is proposed in which information-related data is exploited to address the problem by explicitly editing the generated sentence and enriching the latent representation while maintaining the diversity and information consistency.
- A NeuRetrieval Model for Human-Computer Conversations–
This paper proposes a novel retrieval model named NeuRetrieval for short text understanding, representation and semantic matching and investigates the effectiveness of the proposed deep neural network model for human-computer conversations.
- –
- –
- –
- A Method of Collecting Mongolian Web page Based on Hyperlink Correlation Degree–
The experimental results show that the method of collecting Mongolian web page based on hyperlink correlation degree can effectively enhance the information sum, collection speed and the accuracy rate.
- –
- –
- Quality Analysis of Baotou City High School Biology Examination in 2009–
The quality of Baotou city's high schools biology Examination for 2009 is analyzed in the paper and it is hoped that the analyzing will help improving quality ofBaotou school biology teaching.
- Lexical chunks and spoken language output–
To recognize and master lexical chunks is the key of spoken language output.
- The Role of Setting in Classical Poem and Phrase Teaching–
The flexible application of scene pedagogy in classical poem and phrase is prescribed, and expected teaching aim is achieved by four ways of broadening education space, shortening psychology distance,phasizing role effect, and understanding poem and phrases harmony.
- –
- The Technology of Looking through XML in ASP.NET–
This paper makes some researches in how to look through XML in ASP.NET, and makes some introduction the methods to use XML by DataSet in AS.NET.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.