CNN-based framework for classifying temporal relations with question encoder.

IF 1.6 Q2 INFORMATION SCIENCE & LIBRARY SCIENCE International Journal on Digital Libraries Pub Date : 2022-01-01 Epub Date: 2021-10-13 DOI:10.1007/s00799-021-00310-1
Yohei Seki, Kangkang Zhao, Masaki Oguni, Kazunari Sugiyama
{"title":"CNN-based framework for classifying temporal relations with question encoder.","authors":"Yohei Seki,&nbsp;Kangkang Zhao,&nbsp;Masaki Oguni,&nbsp;Kazunari Sugiyama","doi":"10.1007/s00799-021-00310-1","DOIUrl":null,"url":null,"abstract":"<p><p>Temporal-relation classification plays an important role in the field of natural language processing. Various deep learning-based classifiers, which can generate better models using sentence embedding, have been proposed to address this challenging task. These approaches, however, do not work well due to the lack of task-related information. To overcome this problem, we propose a novel framework that incorporates prior information by employing awareness of events and time expressions (time-event entities) with various window sizes to focus on context words around the entities as a filter. We refer to this module as \"question encoder.\" In our approach, this kind of prior information can extract task-related information from simple sentence embedding. Our experimental results on a publicly available <i>Timebank-Dense</i> corpus demonstrate that our approach outperforms some state-of-the-art techniques, including CNN-, LSTM-, and BERT-based temporal relation classifiers.</p>","PeriodicalId":44974,"journal":{"name":"International Journal on Digital Libraries","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8513567/pdf/","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal on Digital Libraries","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s00799-021-00310-1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2021/10/13 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"INFORMATION SCIENCE & LIBRARY SCIENCE","Score":null,"Total":0}
引用次数: 1

Abstract

Temporal-relation classification plays an important role in the field of natural language processing. Various deep learning-based classifiers, which can generate better models using sentence embedding, have been proposed to address this challenging task. These approaches, however, do not work well due to the lack of task-related information. To overcome this problem, we propose a novel framework that incorporates prior information by employing awareness of events and time expressions (time-event entities) with various window sizes to focus on context words around the entities as a filter. We refer to this module as "question encoder." In our approach, this kind of prior information can extract task-related information from simple sentence embedding. Our experimental results on a publicly available Timebank-Dense corpus demonstrate that our approach outperforms some state-of-the-art techniques, including CNN-, LSTM-, and BERT-based temporal relation classifiers.

Abstract Image

Abstract Image

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于cnn的时间关系问题编码器分类框架。
时间关系分类在自然语言处理领域中占有重要地位。为了解决这一具有挑战性的任务,已经提出了各种基于深度学习的分类器,这些分类器可以使用句子嵌入生成更好的模型。然而,由于缺乏与任务相关的信息,这些方法不能很好地工作。为了克服这个问题,我们提出了一个新的框架,该框架通过使用具有不同窗口大小的事件和时间表达式(时间-事件实体)的感知来融合先验信息,以关注实体周围的上下文词作为过滤器。我们把这个模块称为“问题编码器”。在我们的方法中,这种先验信息可以从简单句嵌入中提取任务相关信息。我们在公开可用的时间银行密集语料库上的实验结果表明,我们的方法优于一些最先进的技术,包括基于CNN、LSTM和bert的时间关系分类器。
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 去求助
来源期刊
CiteScore
4.30
自引率
6.70%
发文量
20
期刊介绍: The International Journal on Digital Libraries (IJDL) examines the theory and practice of acquisition definition organization management preservation and dissemination of digital information via global networking. It covers all aspects of digital libraries (DLs) from large-scale heterogeneous data and information management & access to linking and connectivity to security privacy and policies to its application use and evaluation.The scope of IJDL includes but is not limited to: The FAIR principle and the digital libraries infrastructure Findable: Information access and retrieval; semantic search; data and information exploration; information navigation; smart indexing and searching; resource discovery Accessible: visualization and digital collections; user interfaces; interfaces for handicapped users; HCI and UX in DLs; Security and privacy in DLs; multimodal access Interoperable: metadata (definition management curation integration); syntactic and semantic interoperability; linked data Reusable: reproducibility; Open Science; sustainability profitability repeatability of research results; confidentiality and privacy issues in DLs Digital Library Architectures including heterogeneous and dynamic data management; data and repositories Acquisition of digital information: authoring environments for digital objects; digitization of traditional content Digital Archiving and Preservation Digital Preservation and curation Digital archiving Web Archiving Archiving and preservation Strategies AI for Digital Libraries Machine Learning for DLs Data Mining in DLs NLP for DLs Applications of Digital Libraries Digital Humanities Open Data and their reuse Scholarly DLs (incl. bibliometrics altmetrics) Epigraphy and Paleography Digital Museums Future trends in Digital Libraries Definition of DLs in a ubiquitous digital library world Datafication of digital collections Interaction and user experience (UX) in DLs Information visualization Collection understanding Privacy and security Multimodal user interfaces Accessibility (or "Access for users with disabilities") UX studies
期刊最新文献
Methods for generation, recommendation, exploration and analysis of scholarly publications Comparing free reference extraction pipelines Editorial to the special issue on JCDL 2022 Digital detection of play characters’ relationships in Shakespeare’s plays: extended cross-correlation analysis of the character appearance frequencies Book recommendation system: reviewing different techniques and approaches
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1