TA-SBERT: Token Attention Sentence-BERT for Improving Sentence Representation
Author:
Affiliation:
1. Department of Electrical and Computer Engineering, Inha University, Incheon, Republic of Korea
2. College of Computing, Georgia Institute of Technology, Atlanta, GA, USA
Funder
Korea Agency for Infrastructure Technology Advancement (KAIA) Grant funded through the Ministry of Land, Infrastructure and Transport
Institute of Information & Communications Technology Planning & Evaluation (IITP) Grant funded by the Korea Government (MSIT)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
General Engineering,General Materials Science,General Computer Science
Link
http://xplorestaging.ieee.org/ielx7/6287639/9668973/09749108.pdf?arnumber=9749108
Reference44 articles.
1. Mining and summarizing customer reviews
2. Seeing stars
3. SEM 2013 shared task: Semantic textual similarity;agirre;Proc 2nd Joint Conf Lexical Comput Semantics (SEM),2013
4. Semeval-2012 task 6: A pilot on semantic textual similarity;agirre;Proc 1st Joint Conf Lexical Comput Semantics,2012
5. Mixout: Effective regularization to finetune large-scale pretrained language models;lee;arXiv 1909 11299,2019
Cited by 11 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Enhancing query relevance: leveraging SBERT and cosine similarity for optimal information retrieval;International Journal of Speech Technology;2024-08-16
2. TamilCogniBERT: Enhancing Tamil Language Comprehension using Self Learning;2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS);2024-04-18
3. Chunk2vec: A novel resemblance detection scheme based on Sentence‐BERT for post‐deduplication delta compression in network transmission;IET Communications;2024-01
4. A Trustworthy Automated Short-Answer Scoring System Using a New Dataset and Hybrid Transfer Learning Method;International Journal of Interactive Multimedia and Artificial Intelligence;2024
5. Word-Level Embedding to Improve Performance of Representative Spatio-temporal Document Classification;J INF PROCESS SYST;2023
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3