Loading…
CANDiS: Coupled & Attention-Driven Neural Distant Supervision
Distant Supervision for Relation Extraction uses heuristically aligned text data with an existing knowledge base as training data. The unsupervised nature of this technique allows it to scale to web-scale relation extraction tasks, at the expense of noise in the training data. Previous work has expl...
Saved in:
| Published in: | arXiv.org 2017-10 |
|---|---|
| Main Authors: | , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | |
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Nagarajan, Tushar Sharmistha Talukdar, Partha |
| description | Distant Supervision for Relation Extraction uses heuristically aligned text data with an existing knowledge base as training data. The unsupervised nature of this technique allows it to scale to web-scale relation extraction tasks, at the expense of noise in the training data. Previous work has explored relationships among instances of the same entity-pair to reduce this noise, but relationships among instances across entity-pairs have not been fully exploited. We explore the use of inter-instance couplings based on verb-phrase and entity type similarities. We propose a novel technique, CANDiS, which casts distant supervision using inter-instance coupling into an end-to-end neural network model. CANDiS incorporates an attention module at the instance-level to model the multi-instance nature of this problem. CANDiS outperforms existing state-of-the-art techniques on a standard benchmark dataset. |
| format | article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2076860269</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2076860269</sourcerecordid><originalsourceid>FETCH-proquest_journals_20768602693</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdXb0c8kMtlJwzi8tyElNUVBTcCwpSc0ryczP03UpyixLzVPwSy0tSsxRcMksLknMK1EILi1ILSrLLAaq4GFgTUvMKU7lhdLcDMpuriHOHroFRfmFpanFJfFZ-aVFeUCpeCMDczMLM6DFlsbEqQIA5aw3DA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2076860269</pqid></control><display><type>article</type><title>CANDiS: Coupled & Attention-Driven Neural Distant Supervision</title><source>ProQuest - Publicly Available Content Database</source><creator>Nagarajan, Tushar ; Sharmistha ; Talukdar, Partha</creator><creatorcontrib>Nagarajan, Tushar ; Sharmistha ; Talukdar, Partha</creatorcontrib><description>Distant Supervision for Relation Extraction uses heuristically aligned text data with an existing knowledge base as training data. The unsupervised nature of this technique allows it to scale to web-scale relation extraction tasks, at the expense of noise in the training data. Previous work has explored relationships among instances of the same entity-pair to reduce this noise, but relationships among instances across entity-pairs have not been fully exploited. We explore the use of inter-instance couplings based on verb-phrase and entity type similarities. We propose a novel technique, CANDiS, which casts distant supervision using inter-instance coupling into an end-to-end neural network model. CANDiS incorporates an attention module at the instance-level to model the multi-instance nature of this problem. CANDiS outperforms existing state-of-the-art techniques on a standard benchmark dataset.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Couplings ; Knowledge base ; Neural networks ; Noise reduction ; Supervision ; Training</subject><ispartof>arXiv.org, 2017-10</ispartof><rights>2017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2076860269?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Nagarajan, Tushar</creatorcontrib><creatorcontrib>Sharmistha</creatorcontrib><creatorcontrib>Talukdar, Partha</creatorcontrib><title>CANDiS: Coupled & Attention-Driven Neural Distant Supervision</title><title>arXiv.org</title><description>Distant Supervision for Relation Extraction uses heuristically aligned text data with an existing knowledge base as training data. The unsupervised nature of this technique allows it to scale to web-scale relation extraction tasks, at the expense of noise in the training data. Previous work has explored relationships among instances of the same entity-pair to reduce this noise, but relationships among instances across entity-pairs have not been fully exploited. We explore the use of inter-instance couplings based on verb-phrase and entity type similarities. We propose a novel technique, CANDiS, which casts distant supervision using inter-instance coupling into an end-to-end neural network model. CANDiS incorporates an attention module at the instance-level to model the multi-instance nature of this problem. CANDiS outperforms existing state-of-the-art techniques on a standard benchmark dataset.</description><subject>Couplings</subject><subject>Knowledge base</subject><subject>Neural networks</subject><subject>Noise reduction</subject><subject>Supervision</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdXb0c8kMtlJwzi8tyElNUVBTcCwpSc0ryczP03UpyixLzVPwSy0tSsxRcMksLknMK1EILi1ILSrLLAaq4GFgTUvMKU7lhdLcDMpuriHOHroFRfmFpanFJfFZ-aVFeUCpeCMDczMLM6DFlsbEqQIA5aw3DA</recordid><startdate>20171026</startdate><enddate>20171026</enddate><creator>Nagarajan, Tushar</creator><creator>Sharmistha</creator><creator>Talukdar, Partha</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20171026</creationdate><title>CANDiS: Coupled & Attention-Driven Neural Distant Supervision</title><author>Nagarajan, Tushar ; Sharmistha ; Talukdar, Partha</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20768602693</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Couplings</topic><topic>Knowledge base</topic><topic>Neural networks</topic><topic>Noise reduction</topic><topic>Supervision</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Nagarajan, Tushar</creatorcontrib><creatorcontrib>Sharmistha</creatorcontrib><creatorcontrib>Talukdar, Partha</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>ProQuest - Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nagarajan, Tushar</au><au>Sharmistha</au><au>Talukdar, Partha</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>CANDiS: Coupled & Attention-Driven Neural Distant Supervision</atitle><jtitle>arXiv.org</jtitle><date>2017-10-26</date><risdate>2017</risdate><eissn>2331-8422</eissn><abstract>Distant Supervision for Relation Extraction uses heuristically aligned text data with an existing knowledge base as training data. The unsupervised nature of this technique allows it to scale to web-scale relation extraction tasks, at the expense of noise in the training data. Previous work has explored relationships among instances of the same entity-pair to reduce this noise, but relationships among instances across entity-pairs have not been fully exploited. We explore the use of inter-instance couplings based on verb-phrase and entity type similarities. We propose a novel technique, CANDiS, which casts distant supervision using inter-instance coupling into an end-to-end neural network model. CANDiS incorporates an attention module at the instance-level to model the multi-instance nature of this problem. CANDiS outperforms existing state-of-the-art techniques on a standard benchmark dataset.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2017-10 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2076860269 |
| source | ProQuest - Publicly Available Content Database |
| subjects | Couplings Knowledge base Neural networks Noise reduction Supervision Training |
| title | CANDiS: Coupled & Attention-Driven Neural Distant Supervision |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T12%3A17%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=CANDiS:%20Coupled%20&%20Attention-Driven%20Neural%20Distant%20Supervision&rft.jtitle=arXiv.org&rft.au=Nagarajan,%20Tushar&rft.date=2017-10-26&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2076860269%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20768602693%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2076860269&rft_id=info:pmid/&rfr_iscdi=true |