Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks254 from public data
- Investigating Capsule Networks with Dynamic Routing for Text Classification392
This work proposes three strategies to stabilize the dynamic routing process to alleviate the disturbance of some noise capsules which may contain “background” information or have not been successfully trained.
- A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis344
A new large-scale Multi-Aspect Multi-Sentiment (MAMS) dataset, in which each sentence contains at least two different aspects with different sentiment polarities, and proposes simple yet effective CapsNet and CapsNet-BERT models which combine the strengths of recent NLP advances.
- Large Language Models are Versatile Decomposers: Decomposing Evidence and Questions for Table-based Reasoning288
This work exploits large language models (LLMs) as decomposers for effective table-based reasoning, and proposes a novel ''parsing-execution-filling'' strategy to decompose a complex question into simper step-by-step sub-questions by generating intermediate SQL queries as a bridge.
- GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networks221
A novel non-linear model GCN-GAN is introduced to tackle the challenging temporal link prediction task of weighted dynamic networks and achieves impressive results compared to the state-of-the-art competitors.
- Attention Based LSTM for Target Dependent Sentiment Classification207
An attention-based bidirectional LSTM approach to improve the target-dependent sentiment classification by learning the alignment between the target entities and the most distinguishing features.
- GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection187
GALAXY is a novel pre-trained dialog model that explicitly learns dialog policy from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised learning and has a stronger few-shot ability than existing models under various low-resource settings.
- Generative Adversarial Network for Abstractive Text Summarization178
This paper builds the generator G as an agent of reinforcement learning, which takes the raw text as input and predicts the abstractive summarization, and builds a discriminator which attempts to distinguish the generated summary from the ground truth summary.
- A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers164
This survey provides a comprehensive review of existing deep learning techniques for Relation extraction and proposes a new taxonomy to categorize existing works from three perspectives, i.e., text representation, context encoding, and triplet prediction.
- Multi-Modal Sarcasm Detection with Interactive In-Modal and Cross-Modal Graphs157
This paper explores an interactive graph convolution network (GCN) structure to jointly and interactively learn the incongruity relations of in- modal and cross-modal graphs for determining the significant clues in sarcasm detection and demonstrates that the proposed model achieves state-of-the-art performance.
- Enhancing Cross-target Stance Detection with Transferable Semantic-Emotion Knowledge155
A Semantic-Emotion Knowledge Transferring (SEKT) model for cross-target stance detection is proposed, which uses the external knowledge (semantic and emotion lexicons) as a bridge to enable knowledge transfer across different targets.
- A Survey of Natural Language Generation149
This survey aims to give the latest synthesis of deep learning research on the NLG core tasks, as well as the architectures adopted in the field, and detail meticulously and comprehensively various NLG tasks and datasets.
- 132
- Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction108
A transition-based model is proposed to transform the emotion-cause pair extraction task into a procedure of parsing-like directed graph construction, from which it can recognize emotions with the corresponding causes simultaneously, thereby optimizing separate subtasks jointly and maximizing mutual benefits of tasks interdependently.
- Target-adaptive Graph for Cross-target Stance Detection103
A novel approach that automatically identifies and adapts the target-dependent and target-independent roles that a word plays with respect to a specific target in stance expressions, so as to achieve cross-target stance detection is presented.
- Zero-Shot Stance Detection via Contrastive Learning100
A novel hierarchical contrastive learning strategy is devised to capture the correlation and difference between target-invariant and -specific features and further among different stance labels that allows the model to exploit transferable stance features more effectively for representing the stance of previously unseen targets.
- An ontology-driven clinical decision support system (IDDAP) for infectious disease diagnosis and antibiotic prescription86
This study attempted to bridge the patient/caregiver gap by building a sophisticated application that uses artificial intelligence and machine learning computational techniques to perform data-driven decision-making at the point of primary care.
- Spectral Clustering of Large-scale Data by Directly Solving Normalized Cut79
A new optimization algorithm, namely Direct Normalized Cut (DNC), is proposed to directly optimize the normalized cut model and show the superior performance of BKM, DNC and FNC on large-scale data sets.
- Facial expression recognition with deep learning78
This paper proposes a new method for static facial expression recognition using the CNN model to classify a set of static images into 7 basic emotions and then achieve effective classification automatically.
- 72
- 70
- Boundary-Driven Table-Filling for Aspect Sentiment Triplet Extraction70
Boundary-Driven Table-Filling (BDTF), which represents each triplet as a relation region in the 2D table and transforms the ASTE task into detection and classification of relation regions, is proposed.
- Scalable Normalized Cut with Improved Spectral Rotation70
In the clustering process, an improved spectral rotation method is proposed to obtain the solution of the final clustering assignments and the experimental results show the superior performance of the new Scalable Normalized Cut method.
- Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation69
SPACE is proposed, a novel unified pre-trained dialog model learning from large-scale dialog corpora with limited annotations, which can be effectively fine-tuned on a wide range of downstream dialog tasks.
- Investigating the transferring capability of capsule networks for text classification68
The transferring capability of the proposed cross-domain capsule network (TL-Capsule) is demonstrated by applying it to two transfer learning applications: single-label to multi-label text classification and cross- domain sentiment classification.
- Supervised Feature Selection With a Stratified Feature Weighting Method66
The proposed stratified feature ranking (SFR) method was compared with six feature selection methods on a set of high-dimensional datasets and the results show that SFR was superior to most of these feature selection method.
- Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering65
A question-driven pointer-generator network is designed, which exploits the correlation information between question-answer pairs to aid in attending the essential information when generating answer summaries and a new large-scale CQA corpus is constructed, WikiHowQA, which contains long answers for answer selection as well as reference summaries for answer summarization.
- 65
- 64
- A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis63
A new method to extract emotion cause with a hierarchical neural model and knowledge-based regularizations, which aims to incorporate discourse context information and restrain the parameters by sentiment lexicon and common knowledge is proposed.
- Abstractive Meeting Summarization via Hierarchical Adaptive Segmental Network Learning62
This paper proposes the hierarchical neural encoder based on adaptive recurrent networks to learn the semantic representation of meeting conversation with adaptive conversation segmentation and develops the reinforced decoder network to generate the high-quality summaries for abstractive meeting summarization.
- One-Shot Learning as Instruction Data Prospector for Large Language Models56
It is shown that instruction tuning with the top 1\% of examples curated by \textsc{Nuggets} substantially outperforms conventional methods employing the entire dataset.
- Cross-Domain Sentiment Classification by Capsule Network With Semantic Rules56
A Capsule network for sentiment analysis in domain adaptation scenario with semantic rules (CapsuleDAR) is introduced and a rule network is proposed to incorporate the semantic rules into the capsule network to enhance the comprehensive sentence representation learning.
- A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification54
By using various types of sentiment resources, MEAN utilizes sentiment-relevant information from different representation sub-spaces, which makes it more effective to capture the overall semantics of the sentiment, negation and intensity words for sentiment prediction.
- PLASTIC: Prioritize Long and Short-term Information in Top-n Recommendation using Adversarial Training53
This paper proposes a PLASTIC model, Prioritizing Long And Short-Term Information in top-n reCommendation using adversarial training and shows that this model exhibits significantly better performances on two widely used real-world datasets.
- Few-shot Aspect Category Sentiment Analysis via Meta-learning52
A novel Aspect-Focused Meta-Learning (AFML) framework that constructs aspect-aware and aspect-contrastive representations from external knowledge to match the target aspect with aspects in the training set, and employs the episode-based meta-learning algorithm to train the whole network so as to learn to generalize to novel aspects.
- Feature-enhanced attention network for target-dependent sentiment classification52
A Feature-enhanced Attention Network to improve the performance of target-dependent Sentiment classification (FANS) is proposed and the experimental results demonstrate that FANS has robust superiority over competitors and sets state-of-the-art.
- Dual Learning for Cross-domain Image Captioning48
A dual learning mechanism with a policy gradient method that generates highly rewarded captions is introduced that consistently outperforms previous methods for cross-domain image captioning.
- 47
- Personalized response generation by Dual-learning based domain adaptation46
Experimental results show that the proposed PRGDDA (Personalized Response Generation by Dual-learning based Domain Adaptation) model can generate better personalized responses for different users.
- A Multi-task Learning Approach for Image Captioning46
The experimental results demonstrate that the proposed Multi-task Learning Approach for Image Captioning achieves impressive results compared to other strong competitors.
- A Topic Model for Building Fine-grained Domain-specific Emotion Lexicon45
A novel Emotion-aware LDA (EaLDA) model is proposed to build a domainspecific lexicon for predefined emotions that include anger, disgust, fear, joy, sadness, surprise.
- 44
- Context-based prediction for road traffic state using trajectory pattern mining and recurrent convolutional neural networks44
This study uses a clustering method to group similar trajectories of a particular period together into a cluster for each road, and designs a recurrent convolutional neural network for modeling the complex nonlinear relationship among features to predict road traffic conditions.
- Multitask Learning and Reinforcement Learning for Personalized Dialog Generation: An Empirical Study43
- Hierarchical human-like strategy for aspect-level sentiment classification with sentiment linguistic knowledge and reinforcement learning43
This work proposes a novel Hierarchical Human-like strategy for Aspect-level Sentiment classification (HHAS), which contains three major components, a sentiment-aware mutual attention module, an aspect-specific knowledge distillation module, and a reinforcement learning based re-reading module which are consistent with the stages of the human reading cognitive process.
- Generative adversarial fusion network for class imbalance credit scoring43
An imbalanced generative adversarial fusion network (IGAFN) is proposed to cope with the class imbalance credit scoring based on multi-source heterogeneous credit data and exhibits significantly better performance than the compared methods on two real-life datasets.
- CBN: Constructing a clinical Bayesian network based on data from the electronic medical record43
This study demonstrates that the direct and automated construction of a high-quality health topology and ontology from medical records is feasible and is reproducible.
- Plausibility-promoting generative adversarial network for abstractive text summarization with multi-task constraint40
A plausibility-promoting Generative Adversarial Network for Abstractive Text Summarization with Multi-Task constraint (PGAN-ATSMT), which shows promising performance for generating informative, grammatically correct, and novel summaries.
- DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception38
Compared to the state-of-the-art interleaved content generation models, DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
- Understanding User Behavior in Sina Weibo Online Social Network: A Community Approach37
An information-theoretical measure based on the concept of entropy is introduced to analyze the temporal tweeting behaviors of users and applies a clustering algorithm to divide users into different groups based on their tweeting behaviors, which can improve the design of plenty of applications, such as recommendation systems.
- 36
- Multi-view group representation learning for location-aware group recommendation35
The proposed multi-view group representation learning framework can leverage multiple types of information for deep representation learning of group preferences and incorporate the spatial attributes of locations to further capture the group mobility preferences.
- Interactive Dual Generative Adversarial Networks for Image Captioning35
This paper proposes an Interactive Dual Generative Adversarial Network (IDGAN) for image captioning, which mutually combines the retrieval-based and generation-based methods to learn a better image Captioning ensemble.
- A Generative Model for End-to-End Argument Mining with Reconstructed Positional Encoding and Constrained Pointer Mechanism32
This paper proposes a generative framework, in which the expected outputs of AM are framed as a simple target sequence, and employs a pre-trained sequence-to-sequence language model with a constrained pointer mechanism to model the clues for all the subtasks of AM in the light of the target sequence.
- 32
- 31
- KGDDS: A System for Drug-Drug Similarity Measure in Therapeutic Substitution based on Knowledge Graph Curation31
A system KGDDS for node-link-based bio-medical Knowledge Graph curation and visualization, aiding Drug-Drug Similarity measure, and a user interaction model to allow the user to better understand the drug properties from a drug similarity perspective and gain insights that are not easily observable in individual drugs.
- 30
- 30
- 29
- 29
- Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge28
A context-knowledge interaction learning framework, Knowledge-aware Neural Network, which learns the QA sentence representations by considering a tight interaction with the external knowledge from KG and the textual information and develops two kinds of knowledge-aware attention mechanism to summarize both the context-based and knowledge-based interactions between questions and answers.
- Exploring Human-Like Reading Strategy for Abstractive Text Summarization28
This work proposes a novel Hybrid learning model for Abstractive Text Summarization (HATS), which consists of three major components, a knowledge-based attention network, a multitask encoder-decoder network, and a generative adversarial network, which are consistent with the different stages of the human-like reading strategy.
- 27
- 26
- 26
- 25
- 25
- 25
- 24
- 24
- 24
- 24
- Cross-domain Aspect/Sentiment-aware Abstractive Review Summarization23
The proposed model CASAS (neural attentive model for Cross-domain Aspect/Sentiment-aware Abstractive review Summarization) leverages domain classification task, working on datasets of both source and target domains, to recognize the domain information of texts and transfer knowledge from source domains to target domains.
- 22
- 22
- 22
- Identifying and Tracking Sentiments and Topics from Social Media Texts during Natural Disasters22
The experimental results demonstrate that LDST performs very well at discovering topics and sentiments from social media and tracking their shifts in different geographical regions during emergencies and disasters.
- 22
- 21
- 21
- 20
- 20
- 20
- Attentional Image Retweet Modeling via Multi-Faceted Ranking Network Learning20
A novel attentional multi-faceted ranking network learning framework with multi-modal neural networks is developed for the proposed heterogenous IRM network to learn the joint image tweet representations and user preference representations for prediction task.
- 20
- 19
- Bridging Hierarchical and Sequential Context Modeling for Question-driven Extractive Answer Summarization18
This paper designs a hierarchical compare-aggregate method to integrate the interaction between QA pairs in both word-level and sentence-level into the final question and answer representations and conducts the question-aware sequential extractor to produce a summary for the lengthy answer.
- 18
- 18
- 17
- 17
- 17
- 17
- 16
- MedTruth15
A new truth discovery method is proposed, MedTruth, for medical knowledge condition discovery, which incorporates prior source quality information into the source reliability estimation procedure, and also utilizes the knowledge triple information for trustworthy information computation.
- 15
- 15
- 14
- 14
- 14
- 13
- 13
- 13
- 12
- 11
- 11
- 11
- 11
- 11
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning8
This work proposes VCM, an end-to-end self-supervised visual concept modeling framework that leverages implicit contrastive learning across multiple sampled instances and vision-language fine-tuning to construct a visual concept model without requiring costly concept-level annotations.
- 8
- 8
- Be Relevant, Non-Redundant, and Timely: Deep Reinforcement Learning for Real-Time Event Summarization8
A Deep Reinforcement learning framework for real-time Event Summarization (DRES), which shows promising performance for resolving all three challenges (i.e., relevance, non-redundancy, timeliness) in a unified framework.
- 8
- 8
- 8
- 7
- 7
- Gastroenterology Ontology Construction Using Synonym Identification and Relation Extraction7
The proposed synonym identification and relation extraction method achieves the best performance compared with state-of-the-art methods and also builds a more complete ontology compared with existing gastroenterology disease ontologies.
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- Enhancing Top-N Item Recommendations by Peer Collaboration5
This paper proposes a top-N item recommendation framework called PCRec that leverages collaborative training of two recommender models of the same network structure, termed peer collaboration, and introduces two criteria to identify the importance of parameters of a given recommender model.
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- Learning Max-Margin GeoSocial Multimedia Network Representations for Point-of-Interest Suggestion3
This paper proposes a novel max-margin metric geosocial multimedia network representation learning framework by exploiting users' check-in behavior and their social relations and develops a random-walk based learning method with max- margin metric network embedding.
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognition–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.