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
- Yinglin WangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works93 from public data
- DocRED: A Large-Scale Document-Level Relation Extraction Dataset616
Empirical results show that DocRED is challenging for existing RE methods, which indicates that document-level RE remains an open problem and requires further efforts.
- A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration244
A framework named Dynamic LLM-Agent Network ( DyLAN) is built for LLM-agent collaboration on complicated tasks like reasoning and code generation with reasonable computational cost and an automatic agent team optimization algorithm based on an unsupervised metric termed Agent Importance Score is designed.
- MAVEN: A Massive General Domain Event Detection Dataset232
A MAssive eVENt detection dataset is presented, which contains 4,480 Wikipedia documents, 117,200 event mention instances, and 207 event types and shows that existing ED methods cannot achieve promising results as on the small datasets, which suggests ED in real world remains a challenging task and requires further research efforts.
- Learning from Context or Names? An Empirical Study on Neural Relation Extraction229
An entity-masked contrastive pre-training framework for RE is proposed to gain a deeper understanding on both textual context and type information while avoiding rote memorization of entities or use of superficial cues in mentions.
- MoEfication: Transformer Feed-forward Layers are Mixtures of Experts214
To verify whether functional partitions also emerge in FFNs, it is proposed to convert a model into its MoE version with the same parameters, namely MoEfication, which consists of splitting the parameters of FFNs into multiple functional partitions as experts, and building expert routers to decide which experts will be used for each input.
- RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models164
This work constructs a word-based robustness-aware perturbation to distinguish poisoned samples from clean samples to defend against the backdoor attacks on natural language processing (NLP) models.
- Adversarial Training for Weakly Supervised Event Detection157
The experiments show that the candidate selection and adversarial training can cooperate together to obtain more diverse and accurate training data for ED, and significantly outperform the state-of-the-art methods in various weakly supervised scenarios.
- Rethinking Stealthiness of Backdoor Attack against NLP Models151
A novel word-based backdoor attacking method based on negative data augmentation and modifying word embeddings is proposed, making an important step towards achieving stealthy backdoor attacking.
- Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention146
The multiple layers of the hierarchical attention scheme provide coarse-to-fine granularity to better identify valid instances, which is especially effective for extracting those long-tail relations.
- ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning143
Experimental results demonstrate that ERICA can improve typical PLMs (BERT and RoBERTa) on several language understanding tasks, including relation extraction, entity typing and question answering, especially under low-resource settings.
- CLEVE: Contrastive Pre-training for Event Extraction133
CLEVE is proposed, a contrastive pre-training framework for EE to better learn event knowledge from large unsupervised data and their semantic structures (e.g. AMR) obtained with automatic parsers.
- Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach130
This work highlights a more accurate evaluation setting under the open-world assumption (OWA), which manual checks the correctness of knowledge that is not in KGs and proposes a novel PLM-based KGC model named PKGC, motivated by prompt tuning.
- Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks.125
This paper proposes a multi-instance multi-label convolutional neural network for distantly supervised RE, which first relaxes the expressed-at-least-once assumption, and employs cross-sentence max-pooling so as to enable information sharing across different sentences.
- On Transferability of Prompt Tuning for Natural Language Processing122
It is found that the overlapping rate of activated neurons strongly reflects the transferability, which suggests how the prompts stimulate PLMs is essential, and that prompt transfer is promising for improving PT.
- MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction116
A unified large-scale human-annotated ERE dataset MAVEN-ERE, which contains 103,193 event coreference chains, 1,216,217 temporal relations, 57,992 causal relations, and 15,841 subevent relations, larger than existing datasets of all the ERE tasks by at least an order of magnitude.
- Multi-Granularity Chinese Word Embedding106
Quantitative evaluation demonstrates the superiority of MGE in word similarity computation and analogical reasoning, and Qualitative analysis further shows its capability to identify semantic meanings of words.
- HMEAE: Hierarchical Modular Event Argument Extraction102
A Hierarchical Modular Event Argument Extraction model is proposed, to provide effective inductive bias from the concept hierarchy of event argument roles and significantly outperform the state-of-the-art baselines.
- Joint topic modeling for event summarization across news and social media streams81
This paper proposes a novel unsupervised approach based on topic modeling to summarize trending subjects by jointly discovering the representative and complementary information from news and tweets by co-ranking the news sentences and tweets in both sides simultaneously.
- CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade69
CascadeBERT is proposed, which dynamically selects proper-sized and complete models in a cascading manner, providing comprehensive representations for predictions, and can achieve an overall 15% improvement under 4$\times speed-up compared with existing dynamic early exiting methods.
- Knowledge Inheritance for Pre-trained Language Models66
A pre-training framework named “knowledge inheritance” (KI) is introduced and how could knowledge distillation serve as auxiliary supervision during pre- training to efficiently learn larger PLMs is explored, demonstrating the superiority of KI in training efficiency.
- Generating Templates of Entity Summaries with an Entity-Aspect Model and Pattern Mining61
A novel approach to automatic generation of summary templates from given collections of summary articles by developing an entity-aspect LDA model that automatically grouping of semantically related sentence patterns and automatic identification of template slots that need to be filled in.
- 60
- 54
- Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation50
A novel model is proposed to separate the generation of table-to-text generation into two stages: key fact prediction and surface realization, which needs much fewer annotated data and can be trained with pseudo parallel corpus.
- 46
- 35
- DMRM: A Dual-Channel Multi-Hop Reasoning Model for Visual Dialog35
A novel and more powerful Dual-channel Multi-hop Reasoning Model for Visual Dialog, named DMRM, which synchronously captures information from the dialog history and the image to enrich the semantic representation of the question by exploiting dual-channel reasoning.
- CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild33
This work presents the problem of cross- document RE, making an initial step towards knowledge acquisition in the wild and constructs the first human-annotated cross-document RE dataset CodRED, which is challenging to existing RE methods including strong BERT-based models.
- UTA DLNLP at SemEval-2016 Task 12: Deep Learning Based Natural Language Processing System for Clinical Information Identification from Clinical Notes and Pathology Reports24
A deep neural network based natural language processing system for clinical information extraction from raw clinical notes and pathology reports that uses the context words and their partof-speech tags and shape information as features to learn hidden feature representations.
- Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation23
Experimental results show that the proposed knowledge transfer method can learn new knowledge from diverse language pairs incrementally meanwhile maintaining performance on original language pairs, outperforming various strong baselines in incremental learning for MNMT.
- WeChat Neural Machine Translation Systems for WMT2021
This constrained Chinese→English system is based on the Transformer with effective variants and the DTMT architecture and achieves 36.9 case-sensitive BLEU score, which is the highest among all submissions.
- 19
- Unsupervised Knowledge Selection for Dialogue Generation17
A novel Distilled Distant Supervision Loss (DDSL) is proposed to supervise knowledge selection when the gold knowledge label is unknown and manages to select knowledge more accurately in the unsupervised setting and generates more informative responses, even outperforming many strong supervised baselines.
- CSS-LM: A Contrastive Framework for Semi-Supervised Fine-Tuning of Pre-Trained Language Models16
This work introduces a novel framework (named “CSS-LM”) to improve the fine-tuning phase of PLMs via contrastive semi-supervised learning, which achieves better results than the conventional fine- Tuning strategy on a series of downstream tasks with few-shot settings.
- A Survey of Machine Translation Methods15
The history of machine translation is reviewed and the main methods of machinetranslation are analyzed, and the suggestions on machine translation construction are put forward.
- 11
- 11
- HORNET8
A novel KEPLM named HORNET is proposed, which integrates Heterogeneous knowledge from various structured and unstructured sources into the Roberta NETwork and hence takes full advantage of both linguistic and factual knowledge simultaneously, and design a hybrid attention heterogeneous graph convolution network (HaHGCN).
- 7
- Neural Gibbs Sampling for Joint Event Argument Extraction7
A Bayesian model named Neural Gibbs Sampling (NGS) is proposed to jointly extract event arguments by training two neural networks to model the prior distribution and conditional distribution over event arguments respectively and then using Gibbs sampling to approximate the joint distribution with the learned distributions.
- 6
- Automatically building templates for entity summary construction6
Key features of this novel approach to automatic generation of summary templates from given collections of summary articles include automatic grouping of semantically related sentence patterns and automatic identification of template slots that need to be filled in.
- 5
- 5
- 5
- 4
- 4
- 4
- When Few-Shot Learning Meets Large-Scale Knowledge-Enhanced Pre-training: Alibaba at FewCLUE4
This paper presents the solution to FewCLUE tasks by means of large-scale knowledge-enhanced pre-training over massive texts and knowledge triples, together with a new few-shot learning algorithm for downstream tasks.
- 4
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Event Related Document Retrieval Based on Bipartite Graph2
A novel bipartite graph model is proposed to describe an event, where one bipartition represents event type and the other represents the event specific information, and this model is integrated into the query model for more accurate query representation.
- 2
- 1
- 1
- 1
- 1
- Manual-Guided Dialogue for Flexible Conversational Agents1
This paper introduces three dialogue modeling subtasks: instruction matching, argument filling, and response generation, and reduces the dependence of dialogue models on fine-grained domain ontology, and makes them more flexible to adapt to various domains.
- 1
- 1
- 1
- 1
- 1
- Federated Aggregation via Artificial Bee Colony and Optimal Transport for Distributed Energy Systems–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-16. 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.