paper-with-me

Papers

Entangled Relations: Leveraging NLI and Meta-analysis to Enhance Biomedical Relation Extraction

2024-05-31 · William Hogan, Jingbo Shang

Recent research efforts have explored the potential of leveraging natural language inference (NLI) techniques to enhance relation extraction (RE). In this vein, we introduce MetaEntail-RE, a novel adaptation method that harnesses NLI principles to enhance RE performance. Our approach follows past works by verbalizing relation classes into class-indicative hypotheses, aligning a traditionally multi-class classification task to one of textual entailment. We introduce three key enhancements: (1) Instead of labeling non-entailed premise-hypothesis pairs with the uninformative "neutral" entailment label, we introduce meta-class analysis, which provides additional context by analyzing overarching meta relationships between classes when assigning entailment labels; (2) Feasible hypothesis filtering, which removes unlikely hypotheses from consideration based on pairs of entity types; and (3) Group-based prediction selection, which further improves performance by selecting highly confident predictions. MetaEntail-RE is conceptually simple and empirically powerful, yielding significant improvements over conventional relation extraction techniques and other NLI formulations. Our experimental results underscore the versatility of MetaEntail-RE, demonstrating performance gains across both biomedical and general domains.

📄 PDF Abstract BibTeX arXiv:2406.00226

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-class ClassificationNatural Language InferenceRelationRelation Extraction

Similar Papers 제목 키워드 기반

DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation

2021-06-21 · Yifan Wang, Suyao Tang, Yuntong Lei, Weiping Song 외

Heterogeneous information network has been widely used to alleviate sparsity and cold start problems in recommender systems since it can model rich context information in user-item interactions. Graph neural network is a…

Collaborative FilteringGraph AttentionGraph Neural NetworkRecommendation Systems

Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classification

2024-03-26 · Eva Pachetti, Sotirios A. Tsaftaris, Sara Colantonio

Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We present a strategy for improving the per…

Few-Shot Learningimage-classificationImage ClassificationMedical Image Classification+2

Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models

2026-08-27 · Yiyang Huang, Zhaowen Wang, Simon Jenni, Jing Shi 외 arxiv

Layout understanding, or the interpretation of element organization, is essential for document analysis, user interface (UI) creation, and graphic design. While recent vision-language models (VLMs) excel at interpreting …

LGM: Enhancing Large Language Models with Conceptual Meta-Relations and Iterative Retrieval

2025-11-05 · Wenchang Lei, Ping Zou, Yue Wang, Feng Sun 외 arxiv

Large language models (LLMs) exhibit strong semantic understanding, yet struggle when user instructions involve ambiguous or conceptually misaligned terms. We propose the Language Graph Model (LGM) to enhance conceptual …

Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning

2022-10-01 · Zheng Wu, Yichen Xie, Wenzhao Lian, Changhao Wang 외

Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from relate…

DisentanglementMeta Reinforcement Learningreinforcement-learningReinforcement Learning (RL)