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
- Tat‐Seng ChuaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works86 from public data
- Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences704
It is argued that it is crucial to consider the incomplete nature of KG when incorporating it into recommender system, and a new translation-based recommendation model, which specially accounts for various preferences in translating a user to an item, and jointly train it with a KG completion model by combining several transfer schemes.
- Sequential Recommendation with User Memory Networks555
A memory-augmented neural network (MANN) integrated with the insights of collaborative filtering for recommendation is designed, which store and update users» historical records explicitly, which enhances the expressiveness of the model.
- Benchmarking Foundation Models with Language-Model-as-an-Examiner249
A novel benchmarking framework where the LM serves as a knowledgeable examiner that formulates questions based on its knowledge and evaluates responses in a reference-free manner is proposed, allowing for effortless extensibility as various LMs can be adopted as the examiner and the questions can be constantly updated given more diverse trigger topics.
- Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction193
An effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data is proposed.
- Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate171
This work introduces a formal debate framework (FORD) to conduct a three-stage debate among LLMs with real-world scenarios alignment: fair debate, mismatched debate, and roundtable debate to examine whether LLMs can collaborate effectively to achieve a consensus for a shared goal.
- Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval155
A Tree-augmented Cross-modal Encoding method by jointly learning the linguistic structure of queries and the temporal representation of videos to facilitate video retrieval with complex queries, thereby achieving a better video retrieval performance.
- Improving Event Detection via Open-domain Trigger Knowledge113
A novel Enrichment Knowledge Distillation (EKD) model to leverage external open-domain trigger knowledge to reduce the in-built biases to frequent trigger words in annotations is proposed.
- Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding108
A novel Multi-Prototype Mention Embedding model is proposed, which learns multiple sense embeddings for each mention by jointly modeling words from textual contexts and entities derived from a knowledge base, and an efficient language model based approach to disambiguate each mention to a specific sense.
- Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen87
A new task of expertise style transfer is proposed and a manually annotated dataset is contributed with the goal of alleviating cognitive biases and improving the accuracy and expertise level of laymen descriptions using simple words.
- Low-Resource Name Tagging Learned with Weakly Labeled Data86
A novel neural model for name tagging solely based on weakly labeled (WL) data is proposed, so that it can be applied in any low-resource settings and demonstrate superior performance as well as efficiency.
- 80
- 63
- Who, Where, and What to Wear?55
A novel method to automatically harvest fashion knowledge from social media by using a contextualized fashion concept learning module, which captures the dependencies and correlations among different fashion concepts and introduces a weak label modeling module which can effectively exploit machine-labeled data, a complementary of clean data.
- Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition54
A novel model, Mining Undefined Classes from Other-class (MUCO), that can automatically induce different unde- fined classes from the other class to improve few-shot NER and improve the dis- criminative ability of NER classifier andance the understanding of predefined classes with stand-by semantic knowledge.
- Debiasing NLU Models via Causal Intervention and Counterfactual Reasoning47
This paper shows that there is an unobserved confounder for the natural language utterances and their respective classes, leading to spurious correlations from training data, and provides a new perspective with causal inference to find out the bias.
- Joint Representation Learning of Cross-lingual Words and Entities via Attentive Distant Supervision46
This paper proposes a novel method for joint representation learning of cross-lingual words and entities that captures mutually complementary knowledge, and enables cross-lingsual inferences among knowledge bases and texts.
- Image Enhanced Event Detection in News Articles44
This paper proposes a novel Dual Recurrent Multimodal Model, DRMM, to conduct deep interactions between images and sentences for modality features aggregation and superior performance compared to six state-of-art baselines as well as further ablation studies demonstrate the significance of image modality and effectiveness of the proposed architecture.
- 43
- Interactive Contrastive Learning for Self-Supervised Entity Alignment41
This work conducts bidirectional contrastive learning via building pseudo-aligned entity pairs as pivots to achieve direct cross-KG information interaction and exploits the integration of entity textual and structural information and elaborately designs encoders for better utilization in the self-supervised setting.
- Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks39
This survey probes the core challenges that the rise of LLMs poses for evaluation, and identifies and analyzes two pivotal transitions: from task-specific to capability-based evaluation and from manual to automated evaluation.
- Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction36
This paper proposes a general approach to learn relation prototypes from unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient training data.
- Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution35
A new task of Knowledge-aware Language Model Attribution (KaLMA) is defined that improves upon three core concerns with conventional attributed LMs, and a new ``Conscious Incompetence" setting is proposed considering the incomplete knowledge repository.
- Intuitive or Dependent? Investigating LLMs’ Behavior Style to Conflicting Prompts34
This study investigates the behaviors of Large Language Models when faced with conflicting prompts versus their internal memory to understand LLMs' decision mechanism and establish a complete benchmarking framework including a dataset, a robustness evaluation pipeline, and corresponding metrics.
- Robust Prompt Optimization for Large Language Models Against Distribution Shifts33
This work proposes Generalized Prompt Optimization framework, which incorporates the unlabeled data from the target group into prompt optimization, and demonstrates the effectiveness of the proposed framework with significant performance improvement on thetarget group and comparable performance on the source group.
- Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation Extraction32
This paper proposes a novel DECI model (SENDIR) for better document-level reasoning, different from existing works that build an event graph via linguistic tools, which introduces supportive event pairs for joint modeling.
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 2026-10-12. 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.