利用语义进行答案句子检索

Proceedings of the Eighth Workshop on Exploiting Semantic Annotations in Information Retrieval Pub Date : 2015-10-22 DOI:10.1145/2810133.2810136

Ruey-Cheng Chen, Damiano Spina, W. Bruce Croft, M. Sanderson, Falk Scholer

{"title":"利用语义进行答案句子检索","authors":"Ruey-Cheng Chen, Damiano Spina, W. Bruce Croft, M. Sanderson, Falk Scholer","doi":"10.1145/2810133.2810136","DOIUrl":null,"url":null,"abstract":"Finding answer passages from the Web is a challenging task. One major difficulty is to retrieve sentences that may not have many terms in common with the question. In this paper, we experiment with two semantic approaches for finding non-factoid answers using a learning-to-rank retrieval setting. We show that using semantic representations learned from external resources such as Wikipedia or Google News may substantially improve the quality of top-ranked retrieved answers.","PeriodicalId":298747,"journal":{"name":"Proceedings of the Eighth Workshop on Exploiting Semantic Annotations in Information Retrieval","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"27","resultStr":"{\"title\":\"Harnessing Semantics for Answer Sentence Retrieval\",\"authors\":\"Ruey-Cheng Chen, Damiano Spina, W. Bruce Croft, M. Sanderson, Falk Scholer\",\"doi\":\"10.1145/2810133.2810136\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Finding answer passages from the Web is a challenging task. One major difficulty is to retrieve sentences that may not have many terms in common with the question. In this paper, we experiment with two semantic approaches for finding non-factoid answers using a learning-to-rank retrieval setting. We show that using semantic representations learned from external resources such as Wikipedia or Google News may substantially improve the quality of top-ranked retrieved answers.\",\"PeriodicalId\":298747,\"journal\":{\"name\":\"Proceedings of the Eighth Workshop on Exploiting Semantic Annotations in Information Retrieval\",\"volume\":\"8 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-10-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"27\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Eighth Workshop on Exploiting Semantic Annotations in Information Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2810133.2810136\",\"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 Eighth Workshop on Exploiting Semantic Annotations in Information Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2810133.2810136","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

从网上找到答案是一项具有挑战性的任务。一个主要的困难是检索可能与问题没有很多共同术语的句子。在本文中，我们使用学习排序检索设置实验了两种语义方法来寻找非事实答案。我们表明，使用从外部资源(如维基百科或谷歌新闻)学习的语义表示可能会大大提高排名靠前的检索答案的质量。

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

Harnessing Semantics for Answer Sentence Retrieval

Finding answer passages from the Web is a challenging task. One major difficulty is to retrieve sentences that may not have many terms in common with the question. In this paper, we experiment with two semantic approaches for finding non-factoid answers using a learning-to-rank retrieval setting. We show that using semantic representations learned from external resources such as Wikipedia or Google News may substantially improve the quality of top-ranked retrieved answers.

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

Proceedings of the Eighth Workshop on Exploiting Semantic Annotations in Information Retrieval

自引率

0.00%

发文量