@inproceedings{hershcovich-etal-2018-multitask,
title = "Multitask Parsing Across Semantic Representations",
author = "Hershcovich, Daniel and
Abend, Omri and
Rappoport, Ari",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1035",
doi = "10.18653/v1/P18-1035",
pages = "373--385",
abstract = "The ability to consolidate information of different types is at the core of intelligence, and has tremendous practical value in allowing learning for one task to benefit from generalizations learned for others. In this paper we tackle the challenging task of improving semantic parsing performance, taking UCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD) parsing as auxiliary tasks. We experiment on three languages, using a uniform transition-based system and learning architecture for all parsing tasks. Despite notable conceptual, formal and domain differences, we show that multitask learning significantly improves UCCA parsing in both in-domain and out-of-domain settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hershcovich-etal-2018-multitask">
<titleInfo>
<title>Multitask Parsing Across Semantic Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Abend</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ari</namePart>
<namePart type="family">Rappoport</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The ability to consolidate information of different types is at the core of intelligence, and has tremendous practical value in allowing learning for one task to benefit from generalizations learned for others. In this paper we tackle the challenging task of improving semantic parsing performance, taking UCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD) parsing as auxiliary tasks. We experiment on three languages, using a uniform transition-based system and learning architecture for all parsing tasks. Despite notable conceptual, formal and domain differences, we show that multitask learning significantly improves UCCA parsing in both in-domain and out-of-domain settings.</abstract>
<identifier type="citekey">hershcovich-etal-2018-multitask</identifier>
<identifier type="doi">10.18653/v1/P18-1035</identifier>
<location>
<url>https://aclanthology.org/P18-1035</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>373</start>
<end>385</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multitask Parsing Across Semantic Representations
%A Hershcovich, Daniel
%A Abend, Omri
%A Rappoport, Ari
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F hershcovich-etal-2018-multitask
%X The ability to consolidate information of different types is at the core of intelligence, and has tremendous practical value in allowing learning for one task to benefit from generalizations learned for others. In this paper we tackle the challenging task of improving semantic parsing performance, taking UCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD) parsing as auxiliary tasks. We experiment on three languages, using a uniform transition-based system and learning architecture for all parsing tasks. Despite notable conceptual, formal and domain differences, we show that multitask learning significantly improves UCCA parsing in both in-domain and out-of-domain settings.
%R 10.18653/v1/P18-1035
%U https://aclanthology.org/P18-1035
%U https://doi.org/10.18653/v1/P18-1035
%P 373-385
Markdown (Informal)
[Multitask Parsing Across Semantic Representations](https://aclanthology.org/P18-1035) (Hershcovich et al., ACL 2018)
ACL
- Daniel Hershcovich, Omri Abend, and Ari Rappoport. 2018. Multitask Parsing Across Semantic Representations. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 373–385, Melbourne, Australia. Association for Computational Linguistics.