在可理解性的尖端:语言模型能区分隐喻和无意义吗?

Bernadeta Griciūtė, Marc Tanti, L. Donatelli
{"title":"在可理解性的尖端:语言模型能区分隐喻和无意义吗?","authors":"Bernadeta Griciūtė, Marc Tanti, L. Donatelli","doi":"10.18653/v1/2022.flp-1.25","DOIUrl":null,"url":null,"abstract":"Utterly creative texts can sometimes be difficult to understand, balancing on the edge of comprehensibility. However, good language skills and common sense allow advanced language users both to interpret creative texts and to reject some linguistic input as nonsense. The goal of this paper is to evaluate whether the current language models are also able to make the distinction between a creative language use and nonsense. To test this, we have computed mean rank and pseudo-log-likelihood score (PLL) of metaphorical and nonsensical sentences, and fine-tuned several pretrained models (BERT, RoBERTa) for binary classification between the two categories. There was a significant difference in the mean ranks and PPL scores of the categories, and the classifier reached around 85.5% accuracy. The results raise further questions on what could have let to such satisfactory performance.","PeriodicalId":332745,"journal":{"name":"Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"On the Cusp of Comprehensibility: Can Language Models Distinguish Between Metaphors and Nonsense?\",\"authors\":\"Bernadeta Griciūtė, Marc Tanti, L. Donatelli\",\"doi\":\"10.18653/v1/2022.flp-1.25\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Utterly creative texts can sometimes be difficult to understand, balancing on the edge of comprehensibility. However, good language skills and common sense allow advanced language users both to interpret creative texts and to reject some linguistic input as nonsense. The goal of this paper is to evaluate whether the current language models are also able to make the distinction between a creative language use and nonsense. To test this, we have computed mean rank and pseudo-log-likelihood score (PLL) of metaphorical and nonsensical sentences, and fine-tuned several pretrained models (BERT, RoBERTa) for binary classification between the two categories. There was a significant difference in the mean ranks and PPL scores of the categories, and the classifier reached around 85.5% accuracy. The results raise further questions on what could have let to such satisfactory performance.\",\"PeriodicalId\":332745,\"journal\":{\"name\":\"Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/2022.flp-1.25\",\"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 the 3rd Workshop on Figurative Language Processing (FLP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/2022.flp-1.25","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

完全创造性的文本有时很难理解,在可理解性的边缘平衡。然而,良好的语言技能和常识使高级语言使用者既可以解释创造性文本,又可以将一些语言输入视为无稽之谈。本文的目的是评估当前的语言模型是否也能够区分创造性语言使用和无意义。为了验证这一点,我们计算了隐喻和无意义句子的平均排名和伪对数似然评分(PLL),并对两个类别之间的二元分类的几个预训练模型(BERT, RoBERTa)进行了微调。分类器的平均排名和PPL分数有显著差异,分类器的准确率达到85.5%左右。研究结果进一步提出了一个问题:是什么导致了如此令人满意的表现?
本文章由计算机程序翻译,如有差异,请以英文原文为准。
On the Cusp of Comprehensibility: Can Language Models Distinguish Between Metaphors and Nonsense?
Utterly creative texts can sometimes be difficult to understand, balancing on the edge of comprehensibility. However, good language skills and common sense allow advanced language users both to interpret creative texts and to reject some linguistic input as nonsense. The goal of this paper is to evaluate whether the current language models are also able to make the distinction between a creative language use and nonsense. To test this, we have computed mean rank and pseudo-log-likelihood score (PLL) of metaphorical and nonsensical sentences, and fine-tuned several pretrained models (BERT, RoBERTa) for binary classification between the two categories. There was a significant difference in the mean ranks and PPL scores of the categories, and the classifier reached around 85.5% accuracy. The results raise further questions on what could have let to such satisfactory performance.
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:604180095
Book学术官方微信