Papers by Yafeng Ren

8 papers
MRN: A Locally and Globally Mention-Based Reasoning Network for Document-Level Relation Extraction (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies on document-level relation extraction focus on sentencelevel RE, but recent studies reveal that a large number of relations can actually be expressed through multiple sentences, which necessitates document- level RE.
Approach: They propose a document-level relation extraction model that captures local and global contextual information as well as close and distant mention interactions.
Outcome: The proposed model outperforms state-of-the-art models on three widely used datasets, namely DocRED, CDR, and GDA.
DDGIP: Radiology Report Generation Through Disease Description Graph and Informed Prompting (2025.findings-naacl)

Copied to clipboard

Challenge: Automatic radiology report generation is challenging due to inherent biases in medical imaging data.
Approach: They propose a disease description graph that encapsulates comprehensive and pertinent disease information.
Outcome: The proposed model outperforms state-of-the-art models on two widely-used datasets . the proposed model is based on a three-layer decoder and improves on existing models .
Time-Aware Language Modeling for Historical Text Dating (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to automatic text dating ignore diachronic change of words, which may affect the efforts of text modeling.
Approach: They propose a time-aware language model to learn temporal word representations by transferring language models of general domains to those of time-specific ones and build a hierarchical modeling approach to represent diachronic documents by encoding them with temporal representations.
Outcome: The proposed model outperforms state-of-the-art approaches in historical text dating and other NLP tasks.
Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing work on integrating syntactic information into neural networks uses a single tree, such as a constituency or a dependency tree.
Approach: They propose a method to integrate heterogeneous structure knowledge into a unified sequential LSTM encoder.
Outcome: The proposed method outperforms tree encoders on four syntax-dependent tasks and is efficient and accurate.
Retrofitting Structure-aware Transformer Language Model for End Tasks (2020.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that structure-aware Transformer language model achieves improved perplexity, meanwhile inducing accurate syntactic phrases.
Approach: They propose to exploit syntactic distance to encode phrasal constituency and dependency connection into Transformer language model and leverage it for structure integration.
Outcome: The proposed model achieves significant improvements for both semantic- and syntactic-dependent tasks.
Better Combine Them Together! Integrating Syntactic Constituency and Dependency Representations for Semantic Role Labeling (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies use only one singleton syntax for semantic role labeling (SRL).
Approach: They propose a TreeLSTM-based integration that integrates phrasal boundaries and semantic relations from dependency into a labelaware GCN solution for simultaneously modeling syntactic edges and labels.
Outcome: The proposed system achieves state-of-the-art performance on span-based and dependency-based SRL.
Improving Text Understanding via Deep Syntax-Semantics Communication (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent studies show that integrating syntactic tree models with sequential semantic models can bring improved task performance.
Approach: They propose a deep neural communication model between syntax and semantics to improve the performance of text understanding.
Outcome: The proposed model outperforms baseline models on syntax-dependent tasks by a large margin.
High-order Refining for End-to-end Chinese Semantic Role Labeling (2020.aacl-main)

Copied to clipboard

Challenge: Current semantic role labeling methods are limited to short-term features and local decisions.
Approach: They propose a high-order refining mechanism to perform interaction between all predicate-argument pairs via attention calculation.
Outcome: The proposed model achieves state-of-the-art on Chinese SRL data, including CoNLL09 and Universal Proposition Bank, while relieving the long-range dependency issues.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations