Bigrams和BiLSTMs两种序列隐喻检测的神经网络

Fig-Lang@NAACL-HLT Pub Date : 2018-06-01 DOI:10.18653/v1/W18-0911

Yuri Bizzoni, M. Ghanimifard

{"title":"Bigrams和BiLSTMs两种序列隐喻检测的神经网络","authors":"Yuri Bizzoni, M. Ghanimifard","doi":"10.18653/v1/W18-0911","DOIUrl":null,"url":null,"abstract":"We present and compare two alternative deep neural architectures to perform word-level metaphor detection on text: a bi-LSTM model and a new structure based on recursive feed-forward concatenation of the input. We discuss different versions of such models and the effect that input manipulation - specifically, reducing the length of sentences and introducing concreteness scores for words - have on their performance.","PeriodicalId":190853,"journal":{"name":"Fig-Lang@NAACL-HLT","volume":"123 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"27","resultStr":"{\"title\":\"Bigrams and BiLSTMs Two Neural Networks for Sequential Metaphor Detection\",\"authors\":\"Yuri Bizzoni, M. Ghanimifard\",\"doi\":\"10.18653/v1/W18-0911\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present and compare two alternative deep neural architectures to perform word-level metaphor detection on text: a bi-LSTM model and a new structure based on recursive feed-forward concatenation of the input. We discuss different versions of such models and the effect that input manipulation - specifically, reducing the length of sentences and introducing concreteness scores for words - have on their performance.\",\"PeriodicalId\":190853,\"journal\":{\"name\":\"Fig-Lang@NAACL-HLT\",\"volume\":\"123 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"27\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fig-Lang@NAACL-HLT\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/W18-0911\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fig-Lang@NAACL-HLT","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/W18-0911","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 27

摘要

我们提出并比较了两种可选的深度神经结构来对文本执行词级隐喻检测:一种bi-LSTM模型和一种基于输入的递归前馈连接的新结构。我们讨论了这些模型的不同版本，以及输入操作的影响——特别是减少句子的长度和引入单词的具体得分——对它们的表现有什么影响。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Bigrams and BiLSTMs Two Neural Networks for Sequential Metaphor Detection

We present and compare two alternative deep neural architectures to perform word-level metaphor detection on text: a bi-LSTM model and a new structure based on recursive feed-forward concatenation of the input. We discuss different versions of such models and the effect that input manipulation - specifically, reducing the length of sentences and introducing concreteness scores for words - have on their 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

Fig-Lang@NAACL-HLT

自引率

0.00%

发文量