@inproceedings{tuora-etal-2021-comparing-learnability,
title = "Comparing learnability of two dependency schemes: {`}semantic{'} ({UD}) and {`}syntactic{'} ({SUD})",
author = "Tuora, Ryszard and
Przepi{\'o}rkowski, Adam and
Leczkowski, Aleksander",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.256",
doi = "10.18653/v1/2021.findings-emnlp.256",
pages = "2987--2996",
abstract = "This paper contributes to the thread of research on the learnability of different dependency annotation schemes: one ({`}semantic{'}) favouring content words as heads of dependency relations and the other ({`}syntactic{'}) favouring syntactic heads. Several studies have lent support to the idea that choosing syntactic criteria for assigning heads in dependency trees improves the performance of dependency parsers. This may be explained by postulating that syntactic approaches are generally more learnable. In this study, we test this hypothesis by comparing the performance of five parsing systems (both transition- and graph-based) on a selection of 21 treebanks, each in a {`}semantic{'} variant, represented by standard UD (Universal Dependencies), and a {`}syntactic{'} variant, represented by SUD (Surface-syntactic Universal Dependencies): unlike previously reported experiments, which considered learnability of {`}semantic{'} and {`}syntactic{'} annotations of particular constructions in vitro, the experiments reported here consider whole annotation schemes in vivo. Additionally, we compare these annotation schemes using a range of quantitative syntactic properties, which may also reflect their learnability. The results of the experiments show that SUD tends to be more learnable than UD, but the advantage of one or the other scheme depends on the parser and the corpus in question.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tuora-etal-2021-comparing-learnability">
<titleInfo>
<title>Comparing learnability of two dependency schemes: ‘semantic’ (UD) and ‘syntactic’ (SUD)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryszard</namePart>
<namePart type="family">Tuora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Przepiórkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksander</namePart>
<namePart type="family">Leczkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper contributes to the thread of research on the learnability of different dependency annotation schemes: one (‘semantic’) favouring content words as heads of dependency relations and the other (‘syntactic’) favouring syntactic heads. Several studies have lent support to the idea that choosing syntactic criteria for assigning heads in dependency trees improves the performance of dependency parsers. This may be explained by postulating that syntactic approaches are generally more learnable. In this study, we test this hypothesis by comparing the performance of five parsing systems (both transition- and graph-based) on a selection of 21 treebanks, each in a ‘semantic’ variant, represented by standard UD (Universal Dependencies), and a ‘syntactic’ variant, represented by SUD (Surface-syntactic Universal Dependencies): unlike previously reported experiments, which considered learnability of ‘semantic’ and ‘syntactic’ annotations of particular constructions in vitro, the experiments reported here consider whole annotation schemes in vivo. Additionally, we compare these annotation schemes using a range of quantitative syntactic properties, which may also reflect their learnability. The results of the experiments show that SUD tends to be more learnable than UD, but the advantage of one or the other scheme depends on the parser and the corpus in question.</abstract>
<identifier type="citekey">tuora-etal-2021-comparing-learnability</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.256</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.256</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2987</start>
<end>2996</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing learnability of two dependency schemes: ‘semantic’ (UD) and ‘syntactic’ (SUD)
%A Tuora, Ryszard
%A Przepiórkowski, Adam
%A Leczkowski, Aleksander
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F tuora-etal-2021-comparing-learnability
%X This paper contributes to the thread of research on the learnability of different dependency annotation schemes: one (‘semantic’) favouring content words as heads of dependency relations and the other (‘syntactic’) favouring syntactic heads. Several studies have lent support to the idea that choosing syntactic criteria for assigning heads in dependency trees improves the performance of dependency parsers. This may be explained by postulating that syntactic approaches are generally more learnable. In this study, we test this hypothesis by comparing the performance of five parsing systems (both transition- and graph-based) on a selection of 21 treebanks, each in a ‘semantic’ variant, represented by standard UD (Universal Dependencies), and a ‘syntactic’ variant, represented by SUD (Surface-syntactic Universal Dependencies): unlike previously reported experiments, which considered learnability of ‘semantic’ and ‘syntactic’ annotations of particular constructions in vitro, the experiments reported here consider whole annotation schemes in vivo. Additionally, we compare these annotation schemes using a range of quantitative syntactic properties, which may also reflect their learnability. The results of the experiments show that SUD tends to be more learnable than UD, but the advantage of one or the other scheme depends on the parser and the corpus in question.
%R 10.18653/v1/2021.findings-emnlp.256
%U https://aclanthology.org/2021.findings-emnlp.256
%U https://doi.org/10.18653/v1/2021.findings-emnlp.256
%P 2987-2996
Markdown (Informal)
[Comparing learnability of two dependency schemes: ‘semantic’ (UD) and ‘syntactic’ (SUD)](https://aclanthology.org/2021.findings-emnlp.256) (Tuora et al., Findings 2021)
ACL