Neural Relation Prediction for Simple Question Answering over Knowledge Graph

Knowledge graphs are widely used as a typical resource to provide answers to factoid questions. In simple question answering over knowledge graphs, relation extraction aims to predict the relation of a factoid question from a set of predefined relation types. Most recent methods take advantage of ne...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Abolghasemi, Amin, Momtazi, Saeedeh
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Abolghasemi, Amin
Momtazi, Saeedeh
description Knowledge graphs are widely used as a typical resource to provide answers to factoid questions. In simple question answering over knowledge graphs, relation extraction aims to predict the relation of a factoid question from a set of predefined relation types. Most recent methods take advantage of neural networks to match a question with all predefined relations. In this paper, we propose an instance-based method to capture the underlying relation of question and to this aim, we detect matching paraphrases of a new question which share the same relation, and their corresponding relation is selected as our prediction. The idea of our model roots in the fact that a relation can be expressed with various forms of questions while these forms share lexically or semantically similar terms and concepts. Our experiments on the SimpleQuestions dataset show that the proposed model achieves better accuracy compared to the state-of-the-art relation extraction models.
doi_str_mv 10.48550/arxiv.2002.07715
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2002_07715</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2002_07715</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-f25ef09b2223d35d4524f5264094fe7267d777ffc244d4a0490711440eb744e13</originalsourceid><addsrcrecordid>eNotz81OwzAQBGBfOKDCA3DCL5Cw2ayz5FhVUBDlp6X3yK3XxZKbRA5t4e0RgdOM5jDSp9RVATndGgM3Nn2FY44AmANzYc7V84scko16JdF-hq7Vb0lc2I7Vd0m_h30fRS8PMozbtB1OkkK7091Rkn5qu1MUtxM9T7b_uFBn3sZBLv9zotb3d-vZQ7Z4nT_OpovMVmwyj0Y81BtELF1pHBkkb7AiqMkLY8WOmb3fIpEjC1QDFwURyIaJpCgn6vrvdvQ0fQp7m76bX1czusofIZlHgw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Neural Relation Prediction for Simple Question Answering over Knowledge Graph</title><source>arXiv.org</source><creator>Abolghasemi, Amin ; Momtazi, Saeedeh</creator><creatorcontrib>Abolghasemi, Amin ; Momtazi, Saeedeh</creatorcontrib><description>Knowledge graphs are widely used as a typical resource to provide answers to factoid questions. In simple question answering over knowledge graphs, relation extraction aims to predict the relation of a factoid question from a set of predefined relation types. Most recent methods take advantage of neural networks to match a question with all predefined relations. In this paper, we propose an instance-based method to capture the underlying relation of question and to this aim, we detect matching paraphrases of a new question which share the same relation, and their corresponding relation is selected as our prediction. The idea of our model roots in the fact that a relation can be expressed with various forms of questions while these forms share lexically or semantically similar terms and concepts. Our experiments on the SimpleQuestions dataset show that the proposed model achieves better accuracy compared to the state-of-the-art relation extraction models.</description><identifier>DOI: 10.48550/arxiv.2002.07715</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Learning</subject><creationdate>2020-02</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2002.07715$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2002.07715$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Abolghasemi, Amin</creatorcontrib><creatorcontrib>Momtazi, Saeedeh</creatorcontrib><title>Neural Relation Prediction for Simple Question Answering over Knowledge Graph</title><description>Knowledge graphs are widely used as a typical resource to provide answers to factoid questions. In simple question answering over knowledge graphs, relation extraction aims to predict the relation of a factoid question from a set of predefined relation types. Most recent methods take advantage of neural networks to match a question with all predefined relations. In this paper, we propose an instance-based method to capture the underlying relation of question and to this aim, we detect matching paraphrases of a new question which share the same relation, and their corresponding relation is selected as our prediction. The idea of our model roots in the fact that a relation can be expressed with various forms of questions while these forms share lexically or semantically similar terms and concepts. Our experiments on the SimpleQuestions dataset show that the proposed model achieves better accuracy compared to the state-of-the-art relation extraction models.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz81OwzAQBGBfOKDCA3DCL5Cw2ayz5FhVUBDlp6X3yK3XxZKbRA5t4e0RgdOM5jDSp9RVATndGgM3Nn2FY44AmANzYc7V84scko16JdF-hq7Vb0lc2I7Vd0m_h30fRS8PMozbtB1OkkK7091Rkn5qu1MUtxM9T7b_uFBn3sZBLv9zotb3d-vZQ7Z4nT_OpovMVmwyj0Y81BtELF1pHBkkb7AiqMkLY8WOmb3fIpEjC1QDFwURyIaJpCgn6vrvdvQ0fQp7m76bX1czusofIZlHgw</recordid><startdate>20200218</startdate><enddate>20200218</enddate><creator>Abolghasemi, Amin</creator><creator>Momtazi, Saeedeh</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200218</creationdate><title>Neural Relation Prediction for Simple Question Answering over Knowledge Graph</title><author>Abolghasemi, Amin ; Momtazi, Saeedeh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-f25ef09b2223d35d4524f5264094fe7267d777ffc244d4a0490711440eb744e13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Abolghasemi, Amin</creatorcontrib><creatorcontrib>Momtazi, Saeedeh</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Abolghasemi, Amin</au><au>Momtazi, Saeedeh</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Neural Relation Prediction for Simple Question Answering over Knowledge Graph</atitle><date>2020-02-18</date><risdate>2020</risdate><abstract>Knowledge graphs are widely used as a typical resource to provide answers to factoid questions. In simple question answering over knowledge graphs, relation extraction aims to predict the relation of a factoid question from a set of predefined relation types. Most recent methods take advantage of neural networks to match a question with all predefined relations. In this paper, we propose an instance-based method to capture the underlying relation of question and to this aim, we detect matching paraphrases of a new question which share the same relation, and their corresponding relation is selected as our prediction. The idea of our model roots in the fact that a relation can be expressed with various forms of questions while these forms share lexically or semantically similar terms and concepts. Our experiments on the SimpleQuestions dataset show that the proposed model achieves better accuracy compared to the state-of-the-art relation extraction models.</abstract><doi>10.48550/arxiv.2002.07715</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2002.07715
ispartof
issn
language eng
recordid cdi_arxiv_primary_2002_07715
source arXiv.org
subjects Computer Science - Computation and Language
Computer Science - Learning
title Neural Relation Prediction for Simple Question Answering over Knowledge Graph
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T01%3A35%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Neural%20Relation%20Prediction%20for%20Simple%20Question%20Answering%20over%20Knowledge%20Graph&rft.au=Abolghasemi,%20Amin&rft.date=2020-02-18&rft_id=info:doi/10.48550/arxiv.2002.07715&rft_dat=%3Carxiv_GOX%3E2002_07715%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true