@inproceedings{tian-etal-2022-enhancing,
title = "Enhancing Structure-aware Encoder with Extremely Limited Data for Graph-based Dependency Parsing",
author = "Tian, Yuanhe and
Song, Yan and
Xia, Fei",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.483/",
pages = "5438--5449",
abstract = "Dependency parsing is an important fundamental natural language processing task which analyzes the syntactic structure of an input sentence by illustrating the syntactic relations between words. To improve dependency parsing, leveraging existing dependency parsers and extra data (e.g., through semi-supervised learning) has been demonstrated to be effective, even though the final parsers are trained on inaccurate (but massive) data. In this paper, we propose a frustratingly easy approach to improve graph-based dependency parsing, where a structure-aware encoder is pre-trained on auto-parsed data by predicting the word dependencies and then fine-tuned on gold dependency trees, which differs from the usual pre-training process that aims to predict the context words along dependency paths. Experimental results and analyses demonstrate the effectiveness and robustness of our approach to benefit from the data (even with noise) processed by different parsers, where our approach outperforms strong baselines under different settings with different dependency standards and model architectures used in pre-training and fine-tuning. More importantly, further analyses find that only 2K auto-parsed sentences are required to obtain improvement when pre-training vanilla BERT-large based parser without requiring extra parameters."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tian-etal-2022-enhancing">
<titleInfo>
<title>Enhancing Structure-aware Encoder with Extremely Limited Data for Graph-based Dependency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanhe</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dependency parsing is an important fundamental natural language processing task which analyzes the syntactic structure of an input sentence by illustrating the syntactic relations between words. To improve dependency parsing, leveraging existing dependency parsers and extra data (e.g., through semi-supervised learning) has been demonstrated to be effective, even though the final parsers are trained on inaccurate (but massive) data. In this paper, we propose a frustratingly easy approach to improve graph-based dependency parsing, where a structure-aware encoder is pre-trained on auto-parsed data by predicting the word dependencies and then fine-tuned on gold dependency trees, which differs from the usual pre-training process that aims to predict the context words along dependency paths. Experimental results and analyses demonstrate the effectiveness and robustness of our approach to benefit from the data (even with noise) processed by different parsers, where our approach outperforms strong baselines under different settings with different dependency standards and model architectures used in pre-training and fine-tuning. More importantly, further analyses find that only 2K auto-parsed sentences are required to obtain improvement when pre-training vanilla BERT-large based parser without requiring extra parameters.</abstract>
<identifier type="citekey">tian-etal-2022-enhancing</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.483/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5438</start>
<end>5449</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Structure-aware Encoder with Extremely Limited Data for Graph-based Dependency Parsing
%A Tian, Yuanhe
%A Song, Yan
%A Xia, Fei
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F tian-etal-2022-enhancing
%X Dependency parsing is an important fundamental natural language processing task which analyzes the syntactic structure of an input sentence by illustrating the syntactic relations between words. To improve dependency parsing, leveraging existing dependency parsers and extra data (e.g., through semi-supervised learning) has been demonstrated to be effective, even though the final parsers are trained on inaccurate (but massive) data. In this paper, we propose a frustratingly easy approach to improve graph-based dependency parsing, where a structure-aware encoder is pre-trained on auto-parsed data by predicting the word dependencies and then fine-tuned on gold dependency trees, which differs from the usual pre-training process that aims to predict the context words along dependency paths. Experimental results and analyses demonstrate the effectiveness and robustness of our approach to benefit from the data (even with noise) processed by different parsers, where our approach outperforms strong baselines under different settings with different dependency standards and model architectures used in pre-training and fine-tuning. More importantly, further analyses find that only 2K auto-parsed sentences are required to obtain improvement when pre-training vanilla BERT-large based parser without requiring extra parameters.
%U https://aclanthology.org/2022.coling-1.483/
%P 5438-5449
Markdown (Informal)
[Enhancing Structure-aware Encoder with Extremely Limited Data for Graph-based Dependency Parsing](https://aclanthology.org/2022.coling-1.483/) (Tian et al., COLING 2022)
ACL