Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works109 from public data
- Jointly modeling aspects, ratings and sentiments for movie recommendation (JMARS)464
A probabilistic model based on collaborative filtering and topic modeling is proposed that allows it to capture the interest distribution of users and the content distribution for movies; it provides a link between interest and relevance on a per-aspect basis and it allows us to differentiate between positive and negative sentiments on aPer-Aspect basis.
- Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System259
This paper proposes a novel multi-level cross-view contrastive learning mechanism, named MCCLK, which comprehensively considers three different graph views for KG-aware recommendation, including global-level structural view, local-level collaborative and semantic views, and a k-Nearest-Neighbor item-item semantic graph construction module is proposed.
- CQArank224
This work proposed Topic Expertise Model (TEM), a novel probabilistic generative model with GMM hybrid, to jointly model topics and expertise by integrating textual content model and link structure analysis, and proposed CQARank to measure user interests and expertise score under different topics.
- FaitCrowd199
Experimental results on two real-world datasets show that FaitCrowd can significantly reduce the error rate of aggregation compared with the state-of-the-art multi-source aggregation approaches due to its ability of learning topical expertise from question content and collected answers.
- AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine195
An open-domain chatbot engine that integrates the joint results of Information Retrieval and Sequence to Sequence based generation models and outperforms both IR and generation based models is proposed.
- FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval166
The fashion matching is required to pay much more attention to the fine-grained information in the fashion images and texts, so FashionBERT, which leverages patches as image features, is proposed, which learns high level representations of texts and images.
- Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems151
This paper proposes a learning framework on the top of deep neural matching networks that leverages external knowledge for response ranking in information-seeking conversation systems and incorporates external knowledge into deep neural models with pseudo-relevance feedback and QA correspondence knowledge distillation.
- Kaleido-BERT: Vision-Language Pre-training on Fashion Domain145
A new vision-language (VL) pre-training model dubbed Kaleido-BERT is presented, which introduces a novel kaleido strategy for fashion cross-modality representations from transformers, and design alignment guided masking to jointly focus more on image-text semantic relations.
- Analyzing and Characterizing User Intent in Information-seeking Conversations142
A new dataset designed for this purpose is introduced and used to analyze information-seeking conversations by user intent distribution, co-occurrence, and flow patterns and finds some highly recurring patterns in user intent during an information- seeking process.
- 128
- IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection124
A novel end-to-end scene text detector IncepText is proposed from an instance-aware segmentation perspective and deformable PSROI pooling is introduced to deal with multi-oriented text detection.
- AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience114
In this paper, the AliMe Assist system is demonstrated, the underlying techniques are presented, and the experience in dealing with real-world QA in the E-commerce field is shared.
- User Intent Prediction in Information-seeking Conversations113
This paper extracts features based on the content, structural, and sentiment characteristics of a given utterance, and uses classic machine learning methods to perform user intent prediction, and finds that structural features contribute most to the prediction performance.
- AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search112
A novel compression method that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks and incorporates a task-oriented knowledge distillation loss to provide search hints and an efficiency-aware loss as search constraints, which enables a good trade-off between efficiency and effectiveness for task-adaptive BERT compression.
- Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce105
This paper proposes a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to aresource-poor target domain and proposes an efficient and effective hybrid model by combining a sentence encoding- based method and a sentence interaction-based method as the base model.
- A Hybrid Retrieval-Generation Neural Conversation Model94
This paper proposes a hybrid neural conversation model that combines the merits of both response retrieval and generation methods and shows that the proposed model outperforms both retrieval- based methods and generation-based methods under both automatic evaluation metrics and human evaluation.
- Semantic Analysis and Helpfulness Prediction of Text for Online Product Reviews82
This paper isolates review helpfulness prediction from its outer layer tasks, employ two interpretable semantic features, and use human scoring of helpfulness as ground truth, and results show that the two semantic features can accurately predict helpfulness scores and greatly improve the performance compared with using features previously used.
- Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification75
A novel meta-learning framework integrated with an adversarial domain adaptation network is proposed, aiming to improve the adaptive ability of the model and generate high-quality text embedding for new classes.
- Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains70
This work proposes a Meta-Knowledge Distillation (Meta-KD) framework to build a meta-teacher model that captures transferable knowledge across domains and passes such knowledge to students and demonstrates the effectiveness and superiority of this framework on public multi-domain NLP tasks.
- TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification66
In TransPrompt, a transferable prompting framework for few-shot learning across similar NLP tasks, a multi-task meta-knowledge acquisition procedure is employed to train a meta-learner that captures cross-task transferable knowledge.
- SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining61
In SMedBERT, a medical PLM trained on large-scale medical corpora, incorporating deep structured semantic knowledge from neighbours of linked-entity, the mention-neighbour hybrid attention is proposed to learn heterogeneous-entity information, which infuses the semantic representations of entity types into the homogeneous neighbouring entity structure.
- R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO59
This work proposes Share-GRPO, a novel RL approach that expands the question space for a given question via data transformation techniques, and encourages MLLM to effectively explore diverse reasoning trajectories over the expanded question space and shares the discovered reasoning trajectories across the expanded questions during RL.
- A Minimax Game for Instance based Selective Transfer Learning58
This work proposes a general Minimax Game based model for selective transfer learning that outperforms the competing methods by a large margin and is shown to speed up the training process of the learning task in the target domain than traditional TL methods.
- It Is Not Just What We Say, But How We Say Them: LDA-based Behavior-Topic Model58
Textual information exchanged among users on online social network platforms provides deep understanding into users’ interest and behavioral patterns, which has not yet been well incorporated in the existing topic modeling.
- Artificial Intelligence for Prosthetics: Challenge Solutions55
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector by incorporating expert knowledge and using imitation learning.
- DKPLM: Decomposable Knowledge-Enhanced Pre-trained Language Model for Natural Language Understanding44
A novel KEPLM named DKPLM is proposed that decomposes knowledge injection process of the pre-trained language models in pre-training, fine-tuning and inference stages, which facilitates the applications of KEPLMs in real-world scenarios.
- Learning Topics and Positions from Debatepedia44
A generative model positing latent topics and cross-cutting positions that gives special treatment to person mentions and opinion words is introduced that’s usefulness in attaching opinionated documents to arguments and its consistency with human judgments about positions is evaluated.
- IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems40
This paper analyzes user intent patterns in information-seeking conversations and proposes an intent-aware neural response ranking model “IART”, which refers to “Intent-Aware Ranking with Transformers”.
- A fast divisive clustering algorithm using an improved discrete particle swarm optimizer40
A novel divisive clustering algorithm is proposed by integrating an improved discrete particle swarm optimizer into a divisive clusters framework and shows some promising results.
- Multi-Domain Gated CNN for Review Helpfulness Prediction37
A multi-domain approach that learns domain relationships to help the task by transferring knowledge from data-rich domains to data-deficient domains and gates multi-granularity embeddings in a Neural Network (NN) based transfer learning framework to reflect the domain-variant importance of words.
- 35
- 35
- Modeling User Arguments, Interactions, and Attributes for Stance Prediction in Online Debate Forums35
This work proposes an integrated model to leverage side information, a regression-based latent factor model which jointly models user arguments, interactions, and attributes and demonstrates in experiments that the method has promising results on both micro-level and macro-level stance prediction.
- A Latent Variable Model for Viewpoint Discovery from Threaded Forum Posts34
A principled generative latent variable model which captures three important factors: viewpoint specific topic preference, user identity and user interactions is proposed which clearly outperforms a number of baseline models in terms of both clustering posts based on viewpoints and clustering users with different viewpoints.
- Reinforced History Backtracking for Conversational Question Answering32
This paper proposes a reinforcement learning based method to capture and backtrack the related conversation history to boost model performance and considers both immediate and delayed rewards to guide the reinforced backtracking policy.
- Predicting User’s Political Party Using Ideological Stances32
This work exploits users' ideological stances on controversial issues to predict political party of online users and proposes a collaborative filtering approach to solve the data sparsity problem of users stances on ideological topics and applies clustering method to group the users with the same party.
- 30
- 28
- 28
- Locally Connected Deep Learning Framework for Industrial-scale Recommender Systems28
A locally connected deep learning framework for recommender systems is proposed, which reduces the complexity of deep neural network (DNN) by two to three orders of magnitude and is extended using the idea of the recently proposed Wide&Deep model.
- Exploring global information for session-based recommendation27
This work proposes a basic GNN-based session recommendation model on SBR problem by solely using session-level item-transition information on session graph and proposes a novel approach, called Session-based Recommendation with Global Information (SRGI), which infers the user preferences of the current session via fully exploiting global item- Transition information over all sessions.
- 25
- Personalized Microtopic Recommendation on Microblogs25
This article proposes a joint probabilistic latent factor model to integrate rich information into a matrix factorization-based solution to microtopic recommendation and shows that this model significantly outperforms a few competitive baseline methods, especially in the circumstance where users have few adoption behaviors.
- Modeling interaction features for debate side clustering25
A two-stage solution based on latent variable models is proposed: an interaction feature identification stage to mine interaction features from structured debate posts with known sides and reply intentions; and a clustering stage to incorporate interaction features and model the interplay between interactions and sides for debate side clustering.
- 23
- 22
- 21
- 20
- 17
- 16
- 16
- 16
- 16
- Mining User Relations from Online Discussions using Sentiment Analysis and Probabilistic Matrix Factorization14
Experiments with two tasks show that the learned latent factor representation can give good performance on a relation polarity prediction task and improve the performance of a subgroup detection task.
- 13
- Aspect Extraction from Product Reviews Using Category Hierarchy Information13
An LDA-based generative topic model inducing the two-layer categorical information (CAT-LDA) is proposed, to balance the aspects of both a parent category and its child categories.
- 12
- Exploiting Group-Level Behavior Pattern for Session-Based Recommendation11
In RNMSR, a novel Repeat-aware Neural Mechanism for Session-based Recommendation (RNMSR) is proposed, which combines instance-level and group-level user preference to model the repeat consumption of users, i.e., whether users take repeated consumption and which items are preferred by users.
- Cross-domain Knowledge Distillation for Retrieval-based Question Answering Systems11
This work provides a new perspective on the potential of the teacher-student paradigm facilitating cross-domain transfer learning, where the teacher and student tasks belong to heterogeneous domains, with the goal to improve the student model’s performance in the target domain.
- 10
- 10
- 9
- Query-Oriented Keyphrase Extraction9
The empirical evaluation shows that using a named entity-based phraseness criterion and a language model-based informativeness score gives the best performance on the authors' task, and this method also outperforms two state-of-the-art baseline methods.
- 8
- 7
- 7
- 7
- 7
- 6
- 6
- An Integrated Model for User Attribute Discovery: A Case Study on Political Affiliation Identification6
This work proposes an integrated unsupervised model which takes into consideration all the three components integral to the task of discovering user demographic attributes from social media, and incorporates collaborative filtering with probabilistic matrix factorization to solve the data sparsity problem.
- SueNes: A Weakly Supervised Approach to Evaluating Single-Document Summarization via Negative Sampling5
This paper presents a proof-of-concept study to a weakly supervised summary evaluation approach without the presence of reference summaries, and shows a great advantage in gauging linguistic qualities over all metrics.
- 5
- 5
- 4
- DocAsRef: An Empirical Study on Repurposing Reference-based Summary Quality Metrics as Reference-free Metrics4
After being repurposed reference-freely, the zero-shot BERTScore using the pretrained DeBERTa-large-MNLI model of<0.5B parameters consistently outperforms its original reference-based version across various aspects on the SummEval and Newsroom datasets.
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- Generating Supplementary Travel Guides from Social Media3
This paper proposes to use a latent variable model to align forum threads with the section structure of well-written travel guides and modify an ILP-based summarization method to generate section-specific summaries.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- End-to-end Semantics-based Summary Quality Assessment for Single-document Summarization.2
This work introduces a new end-to-end metric system for summary quality assessment by leveraging the semantic similarities of words and/or sentences in deep learning and exhibits very promising results on gold-standard datasets and suggests its great potential to future summarization research.
- 2
- 1
- Automatic Knowledge Fusion in Transferrable Networks for Semantic Text Matching1
This work proposes a novel method to automatically fuse transferable network architecture that has better performance than the state-of-the-art transfer learning architectures.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.