非语境化嵌入的无监督词汇替换

Takashi Wada, Timothy Baldwin, Yuji Matsumoto, Jey Han Lau
{"title":"非语境化嵌入的无监督词汇替换","authors":"Takashi Wada, Timothy Baldwin, Yuji Matsumoto, Jey Han Lau","doi":"10.48550/arXiv.2209.08236","DOIUrl":null,"url":null,"abstract":"We propose a new unsupervised method for lexical substitution using pre-trained language models. Compared to previous approaches that use the generative capability of language models to predict substitutes, our method retrieves substitutes based on the similarity of contextualised and decontextualised word embeddings, i.e. the average contextual representation of a word in multiple contexts. We conduct experiments in English and Italian, and show that our method substantially outperforms strong baselines and establishes a new state-of-the-art without any explicit supervision or fine-tuning. We further show that our method performs particularly well at predicting low-frequency substitutes, and also generates a diverse list of substitute candidates, reducing morphophonetic or morphosyntactic biases induced by article-noun agreement.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"24 1","pages":"4172-4185"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Unsupervised Lexical Substitution with Decontextualised Embeddings\",\"authors\":\"Takashi Wada, Timothy Baldwin, Yuji Matsumoto, Jey Han Lau\",\"doi\":\"10.48550/arXiv.2209.08236\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a new unsupervised method for lexical substitution using pre-trained language models. Compared to previous approaches that use the generative capability of language models to predict substitutes, our method retrieves substitutes based on the similarity of contextualised and decontextualised word embeddings, i.e. the average contextual representation of a word in multiple contexts. We conduct experiments in English and Italian, and show that our method substantially outperforms strong baselines and establishes a new state-of-the-art without any explicit supervision or fine-tuning. We further show that our method performs particularly well at predicting low-frequency substitutes, and also generates a diverse list of substitute candidates, reducing morphophonetic or morphosyntactic biases induced by article-noun agreement.\",\"PeriodicalId\":91381,\"journal\":{\"name\":\"Proceedings of COLING. International Conference on Computational Linguistics\",\"volume\":\"24 1\",\"pages\":\"4172-4185\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of COLING. International Conference on Computational Linguistics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2209.08236\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of COLING. International Conference on Computational Linguistics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2209.08236","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

我们提出了一种新的使用预训练语言模型进行词汇替换的无监督方法。与之前使用语言模型的生成能力来预测替代品的方法相比,我们的方法基于上下文化和非上下文化词嵌入的相似性来检索替代品,即一个词在多个上下文中的平均上下文表示。我们在英语和意大利语中进行了实验,并表明我们的方法在没有任何明确监督或微调的情况下大大优于强大的基线,并建立了新的最先进的技术。我们进一步表明,我们的方法在预测低频替代方面表现得特别好,并且还生成了一个多样化的替代候选列表,减少了由冠词-名词一致性引起的词音或形态句法偏差。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Unsupervised Lexical Substitution with Decontextualised Embeddings
We propose a new unsupervised method for lexical substitution using pre-trained language models. Compared to previous approaches that use the generative capability of language models to predict substitutes, our method retrieves substitutes based on the similarity of contextualised and decontextualised word embeddings, i.e. the average contextual representation of a word in multiple contexts. We conduct experiments in English and Italian, and show that our method substantially outperforms strong baselines and establishes a new state-of-the-art without any explicit supervision or fine-tuning. We further show that our method performs particularly well at predicting low-frequency substitutes, and also generates a diverse list of substitute candidates, reducing morphophonetic or morphosyntactic biases induced by article-noun agreement.
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
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:481959085
Book学术官方微信