Improving Document-level Relation Extraction via Contextualizing Mention Representations andWeighting Mention Pairs

Ping Jiang, Xian-Ling Mao, Bin-Bin Bian, Heyan Huang
{"title":"Improving Document-level Relation Extraction via Contextualizing Mention Representations andWeighting Mention Pairs","authors":"Ping Jiang, Xian-Ling Mao, Bin-Bin Bian, Heyan Huang","doi":"10.1109/ICBK50248.2020.00051","DOIUrl":null,"url":null,"abstract":"Document-level relation extraction (RE) has attracted considerable attention, because a large number of relational facts are expressed in multiple sentences. Recently, encoder-aggregator based models have become promising for document-level RE. However, these models have two shortcomings: (i) they cannot obtain contextualized representations of a mention by low computational cost, when the mention is involved in different entity pairs; (ii) they ignore the different weights for the mention pairs of a target entity pair. To tackle the above two problems, in this paper, we propose a novel encoder-attender-aggregator model, which introduces two attenders between the encoder and aggregator. Specifically, a mutual attender is first employed on the selected head and tail mentions to efficiently produce contextualized mention representations. Then, an integration attender is utilized to weight the mention pairs of a target entity pair. Extensive experiments on two document-level RE datasets show that the proposed model performs better than the state-of-the-art baselines. Our codes are publicly available at “https://github.com/nefujiangping/EncAttAgg”.","PeriodicalId":432857,"journal":{"name":"2020 IEEE International Conference on Knowledge Graph (ICKG)","volume":"263 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Conference on Knowledge Graph (ICKG)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICBK50248.2020.00051","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Document-level relation extraction (RE) has attracted considerable attention, because a large number of relational facts are expressed in multiple sentences. Recently, encoder-aggregator based models have become promising for document-level RE. However, these models have two shortcomings: (i) they cannot obtain contextualized representations of a mention by low computational cost, when the mention is involved in different entity pairs; (ii) they ignore the different weights for the mention pairs of a target entity pair. To tackle the above two problems, in this paper, we propose a novel encoder-attender-aggregator model, which introduces two attenders between the encoder and aggregator. Specifically, a mutual attender is first employed on the selected head and tail mentions to efficiently produce contextualized mention representations. Then, an integration attender is utilized to weight the mention pairs of a target entity pair. Extensive experiments on two document-level RE datasets show that the proposed model performs better than the state-of-the-art baselines. Our codes are publicly available at “https://github.com/nefujiangping/EncAttAgg”.
通过上下文化提及表示和加权提及对改进文档级关系提取
文档级关系抽取(RE)由于在多个句子中表达了大量的关系事实而引起了人们的广泛关注。最近,基于编码器-聚合器的模型在文档级RE中变得很有前途。然而,这些模型有两个缺点:(i)当提及涉及不同的实体对时,由于计算成本低,它们无法获得提及的上下文化表示;(ii)它们忽略了目标实体对的提及对的不同权重。为了解决上述两个问题,本文提出了一种新的编码器-参与者-聚合器模型,该模型在编码器和聚合器之间引入两个参与者。具体而言,首先在选定的头和尾提及上使用互参与者,以有效地产生上下文化的提及表示。然后,利用集成参与者对目标实体对的提及对进行加权。在两个文档级RE数据集上进行的大量实验表明,所提出的模型比最先进的基线性能更好。我们的代码可在“https://github.com/nefujiangping/EncAttAgg”公开获取。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信