Broad-Coverage Semantic Parsing as Transduction

We unify different broad-coverage semantic parsing tasks under a transduction paradigm, and propose an attention-based neural framework that incrementally builds a meaning representation via a sequence of semantic relations. By leveraging multiple attention mechanisms, the transducer can be effectiv...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-11
Main Authors: Zhang, Sheng, Ma, Xutai, Duh, Kevin, Benjamin Van Durme
Format: Article
Language:English
Subjects:
Semantics
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 Zhang, Sheng
Ma, Xutai
Duh, Kevin
Benjamin Van Durme
description We unify different broad-coverage semantic parsing tasks under a transduction paradigm, and propose an attention-based neural framework that incrementally builds a meaning representation via a sequence of semantic relations. By leveraging multiple attention mechanisms, the transducer can be effectively trained without relying on a pre-trained aligner. Experiments conducted on three separate broad-coverage semantic parsing tasks -- AMR, SDP and UCCA -- demonstrate that our attention-based neural transducer improves the state of the art on both AMR and UCCA, and is competitive with the state of the art on SDP.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2287214868</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2287214868</sourcerecordid><originalsourceid>FETCH-proquest_journals_22872148683</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQdyrKT0zRdc4vSy1KTE9VCE7NTcwryUxWCEgsKs7MS1dILFYIKUrMK04pTS7JzM_jYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IyMLcyNDEwszC2PiVAEAHykyrw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2287214868</pqid></control><display><type>article</type><title>Broad-Coverage Semantic Parsing as Transduction</title><source>Publicly Available Content Database</source><creator>Zhang, Sheng ; Ma, Xutai ; Duh, Kevin ; Benjamin Van Durme</creator><creatorcontrib>Zhang, Sheng ; Ma, Xutai ; Duh, Kevin ; Benjamin Van Durme</creatorcontrib><description>We unify different broad-coverage semantic parsing tasks under a transduction paradigm, and propose an attention-based neural framework that incrementally builds a meaning representation via a sequence of semantic relations. By leveraging multiple attention mechanisms, the transducer can be effectively trained without relying on a pre-trained aligner. Experiments conducted on three separate broad-coverage semantic parsing tasks -- AMR, SDP and UCCA -- demonstrate that our attention-based neural transducer improves the state of the art on both AMR and UCCA, and is competitive with the state of the art on SDP.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Semantics</subject><ispartof>arXiv.org, 2019-11</ispartof><rights>2019. 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/2287214868?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Zhang, Sheng</creatorcontrib><creatorcontrib>Ma, Xutai</creatorcontrib><creatorcontrib>Duh, Kevin</creatorcontrib><creatorcontrib>Benjamin Van Durme</creatorcontrib><title>Broad-Coverage Semantic Parsing as Transduction</title><title>arXiv.org</title><description>We unify different broad-coverage semantic parsing tasks under a transduction paradigm, and propose an attention-based neural framework that incrementally builds a meaning representation via a sequence of semantic relations. By leveraging multiple attention mechanisms, the transducer can be effectively trained without relying on a pre-trained aligner. Experiments conducted on three separate broad-coverage semantic parsing tasks -- AMR, SDP and UCCA -- demonstrate that our attention-based neural transducer improves the state of the art on both AMR and UCCA, and is competitive with the state of the art on SDP.</description><subject>Semantics</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQdyrKT0zRdc4vSy1KTE9VCE7NTcwryUxWCEgsKs7MS1dILFYIKUrMK04pTS7JzM_jYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IyMLcyNDEwszC2PiVAEAHykyrw</recordid><startdate>20191104</startdate><enddate>20191104</enddate><creator>Zhang, Sheng</creator><creator>Ma, Xutai</creator><creator>Duh, Kevin</creator><creator>Benjamin Van Durme</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>20191104</creationdate><title>Broad-Coverage Semantic Parsing as Transduction</title><author>Zhang, Sheng ; Ma, Xutai ; Duh, Kevin ; Benjamin Van Durme</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_22872148683</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Semantics</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Sheng</creatorcontrib><creatorcontrib>Ma, Xutai</creatorcontrib><creatorcontrib>Duh, Kevin</creatorcontrib><creatorcontrib>Benjamin Van Durme</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; 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>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>Zhang, Sheng</au><au>Ma, Xutai</au><au>Duh, Kevin</au><au>Benjamin Van Durme</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Broad-Coverage Semantic Parsing as Transduction</atitle><jtitle>arXiv.org</jtitle><date>2019-11-04</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>We unify different broad-coverage semantic parsing tasks under a transduction paradigm, and propose an attention-based neural framework that incrementally builds a meaning representation via a sequence of semantic relations. By leveraging multiple attention mechanisms, the transducer can be effectively trained without relying on a pre-trained aligner. Experiments conducted on three separate broad-coverage semantic parsing tasks -- AMR, SDP and UCCA -- demonstrate that our attention-based neural transducer improves the state of the art on both AMR and UCCA, and is competitive with the state of the art on SDP.</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, 2019-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_2287214868
source Publicly Available Content Database
subjects Semantics
title Broad-Coverage Semantic Parsing as Transduction
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T22%3A35%3A08IST&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=Broad-Coverage%20Semantic%20Parsing%20as%20Transduction&rft.jtitle=arXiv.org&rft.au=Zhang,%20Sheng&rft.date=2019-11-04&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2287214868%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_22872148683%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2287214868&rft_id=info:pmid/&rfr_iscdi=true