Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mai, Chengcheng, Wang, Yuxiang, Gong, Ziyu, Wang, Hanxiang, Huang, Yihua
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2501.00571
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916878611382272
author Mai, Chengcheng
Wang, Yuxiang
Gong, Ziyu
Wang, Hanxiang
Huang, Yihua
author_facet Mai, Chengcheng
Wang, Yuxiang
Gong, Ziyu
Wang, Hanxiang
Huang, Yihua
contents Document-level relation extraction (Doc-RE) aims to extract relations between entities across multiple sentences. Therefore, Doc-RE requires more comprehensive reasoning abilities like humans, involving complex cross-sentence interactions between entities, contexts, and external general knowledge, compared to the sentence-level RE. However, most existing Doc-RE methods focus on optimizing single reasoning ability, but lack the ability to utilize external knowledge for comprehensive reasoning on long documents. To solve these problems, a knowledge retrieval augmented method, named KnowRA, was proposed with comprehensive reasoning to autonomously determine whether to accept external knowledge to assist DocRE. Firstly, we constructed a document graph for semantic encoding and integrated the co-reference resolution model to augment the co-reference reasoning ability. Then, we expanded the document graph into a document knowledge graph by retrieving the external knowledge base for common-sense reasoning and a novel knowledge filtration method was presented to filter out irrelevant knowledge. Finally, we proposed the axis attention mechanism to build direct and indirect associations with intermediary entities for achieving cross-sentence logical reasoning. Extensive experiments conducted on two datasets verified the effectiveness of our method compared to the state-of-the-art baselines. Our code is available at https://anonymous.4open.science/r/KnowRA.
format Preprint
id arxiv_https___arxiv_org_abs_2501_00571
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities
Mai, Chengcheng
Wang, Yuxiang
Gong, Ziyu
Wang, Hanxiang
Huang, Yihua
Computation and Language
Document-level relation extraction (Doc-RE) aims to extract relations between entities across multiple sentences. Therefore, Doc-RE requires more comprehensive reasoning abilities like humans, involving complex cross-sentence interactions between entities, contexts, and external general knowledge, compared to the sentence-level RE. However, most existing Doc-RE methods focus on optimizing single reasoning ability, but lack the ability to utilize external knowledge for comprehensive reasoning on long documents. To solve these problems, a knowledge retrieval augmented method, named KnowRA, was proposed with comprehensive reasoning to autonomously determine whether to accept external knowledge to assist DocRE. Firstly, we constructed a document graph for semantic encoding and integrated the co-reference resolution model to augment the co-reference reasoning ability. Then, we expanded the document graph into a document knowledge graph by retrieving the external knowledge base for common-sense reasoning and a novel knowledge filtration method was presented to filter out irrelevant knowledge. Finally, we proposed the axis attention mechanism to build direct and indirect associations with intermediary entities for achieving cross-sentence logical reasoning. Extensive experiments conducted on two datasets verified the effectiveness of our method compared to the state-of-the-art baselines. Our code is available at https://anonymous.4open.science/r/KnowRA.
title KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities
topic Computation and Language
url https://arxiv.org/abs/2501.00571