感官改造模型的推广

IF 2.3 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Natural Language Engineering Pub Date : 2023-03-31 DOI:10.1017/S1351324922000523
Yang-Yin Lee, Ting-Yu Yen, Hen-Hsen Huang, Yow-Ting Shiue, Hsin-Hsi Chen
{"title":"感官改造模型的推广","authors":"Yang-Yin Lee, Ting-Yu Yen, Hen-Hsen Huang, Yow-Ting Shiue, Hsin-Hsi Chen","doi":"10.1017/S1351324922000523","DOIUrl":null,"url":null,"abstract":"Abstract With the aid of recently proposed word embedding algorithms, the study of semantic relatedness has progressed rapidly. However, word-level representations are still lacking for many natural language processing tasks. Various sense-level embedding learning algorithms have been proposed to address this issue. In this paper, we present a generalized model derived from existing sense retrofitting models. In this generalization, we take into account semantic relations between the senses, relation strength, and semantic strength. Experimental results show that the generalized model outperforms previous approaches on four tasks: semantic relatedness, contextual word similarity, semantic difference, and synonym selection. Based on the generalized sense retrofitting model, we also propose a standardization process on the dimensions with four settings, a neighbor expansion process from the nearest neighbors, and combinations of these two approaches. Finally, we propose a Procrustes analysis approach that inspired from bilingual mapping models for learning representations that outside of the ontology. The experimental results show the advantages of these approaches on semantic relatedness tasks.","PeriodicalId":49143,"journal":{"name":"Natural Language Engineering","volume":"29 1","pages":"1097 - 1125"},"PeriodicalIF":2.3000,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"On generalization of the sense retrofitting model\",\"authors\":\"Yang-Yin Lee, Ting-Yu Yen, Hen-Hsen Huang, Yow-Ting Shiue, Hsin-Hsi Chen\",\"doi\":\"10.1017/S1351324922000523\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract With the aid of recently proposed word embedding algorithms, the study of semantic relatedness has progressed rapidly. However, word-level representations are still lacking for many natural language processing tasks. Various sense-level embedding learning algorithms have been proposed to address this issue. In this paper, we present a generalized model derived from existing sense retrofitting models. In this generalization, we take into account semantic relations between the senses, relation strength, and semantic strength. Experimental results show that the generalized model outperforms previous approaches on four tasks: semantic relatedness, contextual word similarity, semantic difference, and synonym selection. Based on the generalized sense retrofitting model, we also propose a standardization process on the dimensions with four settings, a neighbor expansion process from the nearest neighbors, and combinations of these two approaches. Finally, we propose a Procrustes analysis approach that inspired from bilingual mapping models for learning representations that outside of the ontology. The experimental results show the advantages of these approaches on semantic relatedness tasks.\",\"PeriodicalId\":49143,\"journal\":{\"name\":\"Natural Language Engineering\",\"volume\":\"29 1\",\"pages\":\"1097 - 1125\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2023-03-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Natural Language Engineering\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1017/S1351324922000523\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Natural Language Engineering","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1017/S1351324922000523","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

摘要在最近提出的单词嵌入算法的帮助下,语义相关性的研究进展迅速。然而,对于许多自然语言处理任务来说,单词级表示仍然缺乏。已经提出了各种感觉级嵌入学习算法来解决这个问题。在本文中,我们提出了一个广义模型,该模型是从现有的感官改造模型推导而来的。在这种概括中,我们考虑了感官之间的语义关系、关系强度和语义强度。实验结果表明,该广义模型在语义关联性、上下文词相似度、语义差异和同义词选择四个方面优于以往的方法。在广义意义改造模型的基础上,我们还提出了一个具有四个设置的维度标准化过程,一个从最近邻居扩展邻居的过程,以及这两种方法的组合。最后,我们提出了一种Procrustes分析方法,该方法的灵感来自双语映射模型,用于学习本体之外的表示。实验结果表明了这些方法在语义关联任务中的优势。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
On generalization of the sense retrofitting model
Abstract With the aid of recently proposed word embedding algorithms, the study of semantic relatedness has progressed rapidly. However, word-level representations are still lacking for many natural language processing tasks. Various sense-level embedding learning algorithms have been proposed to address this issue. In this paper, we present a generalized model derived from existing sense retrofitting models. In this generalization, we take into account semantic relations between the senses, relation strength, and semantic strength. Experimental results show that the generalized model outperforms previous approaches on four tasks: semantic relatedness, contextual word similarity, semantic difference, and synonym selection. Based on the generalized sense retrofitting model, we also propose a standardization process on the dimensions with four settings, a neighbor expansion process from the nearest neighbors, and combinations of these two approaches. Finally, we propose a Procrustes analysis approach that inspired from bilingual mapping models for learning representations that outside of the ontology. The experimental results show the advantages of these approaches on semantic relatedness tasks.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Natural Language Engineering
Natural Language Engineering COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-
CiteScore
5.90
自引率
12.00%
发文量
60
审稿时长
>12 weeks
期刊介绍: Natural Language Engineering meets the needs of professionals and researchers working in all areas of computerised language processing, whether from the perspective of theoretical or descriptive linguistics, lexicology, computer science or engineering. Its aim is to bridge the gap between traditional computational linguistics research and the implementation of practical applications with potential real-world use. As well as publishing research articles on a broad range of topics - from text analysis, machine translation, information retrieval and speech analysis and generation to integrated systems and multi modal interfaces - it also publishes special issues on specific areas and technologies within these topics, an industry watch column and book reviews.
期刊最新文献
Start-up activity in the LLM ecosystem Anisotropic span embeddings and the negative impact of higher-order inference for coreference resolution: An empirical analysis Automated annotation of parallel bible corpora with cross-lingual semantic concordance How do control tokens affect natural language generation tasks like text simplification Emerging trends: When can users trust GPT, and when should they intervene?
×
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