@inproceedings{strzyz-etal-2019-sequence,
title = "Sequence Labeling Parsing by Learning across Representations",
author = "Strzyz, Michalina and
Vilares, David and
G{\'o}mez-Rodr{\'\i}guez, Carlos",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1531",
doi = "10.18653/v1/P19-1531",
pages = "5350--5357",
abstract = "We use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions. To do so, we cast the problem as multitask learning (MTL). First, we show that adding a parsing paradigm as an auxiliary loss consistently improves the performance on the other paradigm. Secondly, we explore an MTL sequence labeling model that parses both representations, at almost no cost in terms of performance and speed. The results across the board show that on average MTL models with auxiliary losses for constituency parsing outperform single-task ones by 1.05 F1 points, and for dependency parsing by 0.62 UAS points.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strzyz-etal-2019-sequence">
<titleInfo>
<title>Sequence Labeling Parsing by Learning across Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michalina</namePart>
<namePart type="family">Strzyz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vilares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Gómez-Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions. To do so, we cast the problem as multitask learning (MTL). First, we show that adding a parsing paradigm as an auxiliary loss consistently improves the performance on the other paradigm. Secondly, we explore an MTL sequence labeling model that parses both representations, at almost no cost in terms of performance and speed. The results across the board show that on average MTL models with auxiliary losses for constituency parsing outperform single-task ones by 1.05 F1 points, and for dependency parsing by 0.62 UAS points.</abstract>
<identifier type="citekey">strzyz-etal-2019-sequence</identifier>
<identifier type="doi">10.18653/v1/P19-1531</identifier>
<location>
<url>https://aclanthology.org/P19-1531</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>5350</start>
<end>5357</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sequence Labeling Parsing by Learning across Representations
%A Strzyz, Michalina
%A Vilares, David
%A Gómez-Rodríguez, Carlos
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F strzyz-etal-2019-sequence
%X We use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions. To do so, we cast the problem as multitask learning (MTL). First, we show that adding a parsing paradigm as an auxiliary loss consistently improves the performance on the other paradigm. Secondly, we explore an MTL sequence labeling model that parses both representations, at almost no cost in terms of performance and speed. The results across the board show that on average MTL models with auxiliary losses for constituency parsing outperform single-task ones by 1.05 F1 points, and for dependency parsing by 0.62 UAS points.
%R 10.18653/v1/P19-1531
%U https://aclanthology.org/P19-1531
%U https://doi.org/10.18653/v1/P19-1531
%P 5350-5357
Markdown (Informal)
[Sequence Labeling Parsing by Learning across Representations](https://aclanthology.org/P19-1531) (Strzyz et al., ACL 2019)
ACL