@article{liu-etal-2021-universal,
title = "Universal Discourse Representation Structure Parsing",
author = "Liu, Jiangming and
Cohen, Shay B. and
Lapata, Mirella and
Bos, Johan",
journal = "Computational Linguistics",
volume = "47",
number = "2",
month = jun,
year = "2021",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2021.cl-2.15",
doi = "10.1162/coli_a_00406",
pages = "445--476",
abstract = "We consider the task of crosslingual semantic parsing in the style of Discourse Representation Theory (DRT) where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide learning in other languages. We introduce 𝕌niversal Discourse Representation Theory (𝕌DRT), a variant of DRT that explicitly anchors semantic representations to tokens in the linguistic input. We develop a semantic parsing framework based on the Transformer architecture and utilize it to obtain semantic resources in multiple languages following two learning schemes. The many-to-one approach translates non-English text to English, and then runs a relatively accurate English parser on the translated text, while the one-to-many approach translates gold standard English to non-English text and trains multiple parsers (one per language) on the translations. Experimental results on the Parallel Meaning Bank show that our proposal outperforms strong baselines by a wide margin and can be used to construct (silver-standard) meaning banks for 99 languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-universal">
<titleInfo>
<title>Universal Discourse Representation Structure Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiangming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johan</namePart>
<namePart type="family">Bos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We consider the task of crosslingual semantic parsing in the style of Discourse Representation Theory (DRT) where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide learning in other languages. We introduce 𝕌niversal Discourse Representation Theory (𝕌DRT), a variant of DRT that explicitly anchors semantic representations to tokens in the linguistic input. We develop a semantic parsing framework based on the Transformer architecture and utilize it to obtain semantic resources in multiple languages following two learning schemes. The many-to-one approach translates non-English text to English, and then runs a relatively accurate English parser on the translated text, while the one-to-many approach translates gold standard English to non-English text and trains multiple parsers (one per language) on the translations. Experimental results on the Parallel Meaning Bank show that our proposal outperforms strong baselines by a wide margin and can be used to construct (silver-standard) meaning banks for 99 languages.</abstract>
<identifier type="citekey">liu-etal-2021-universal</identifier>
<identifier type="doi">10.1162/coli_a_00406</identifier>
<location>
<url>https://aclanthology.org/2021.cl-2.15</url>
</location>
<part>
<date>2021-06</date>
<detail type="volume"><number>47</number></detail>
<detail type="issue"><number>2</number></detail>
<extent unit="page">
<start>445</start>
<end>476</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Universal Discourse Representation Structure Parsing
%A Liu, Jiangming
%A Cohen, Shay B.
%A Lapata, Mirella
%A Bos, Johan
%J Computational Linguistics
%D 2021
%8 June
%V 47
%N 2
%I MIT Press
%C Cambridge, MA
%F liu-etal-2021-universal
%X We consider the task of crosslingual semantic parsing in the style of Discourse Representation Theory (DRT) where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide learning in other languages. We introduce 𝕌niversal Discourse Representation Theory (𝕌DRT), a variant of DRT that explicitly anchors semantic representations to tokens in the linguistic input. We develop a semantic parsing framework based on the Transformer architecture and utilize it to obtain semantic resources in multiple languages following two learning schemes. The many-to-one approach translates non-English text to English, and then runs a relatively accurate English parser on the translated text, while the one-to-many approach translates gold standard English to non-English text and trains multiple parsers (one per language) on the translations. Experimental results on the Parallel Meaning Bank show that our proposal outperforms strong baselines by a wide margin and can be used to construct (silver-standard) meaning banks for 99 languages.
%R 10.1162/coli_a_00406
%U https://aclanthology.org/2021.cl-2.15
%U https://doi.org/10.1162/coli_a_00406
%P 445-476
Markdown (Informal)
[Universal Discourse Representation Structure Parsing](https://aclanthology.org/2021.cl-2.15) (Liu et al., CL 2021)
ACL