@inproceedings{lin-etal-2022-dependency,
title = "Dependency Parsing via Sequence Generation",
author = "Lin, Boda and
Yao, Zijun and
Shi, Jiaxin and
Cao, Shulin and
Tang, Binghao and
Li, Si and
Luo, Yong and
Li, Juanzi and
Hou, Lei",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.543",
doi = "10.18653/v1/2022.findings-emnlp.543",
pages = "7339--7353",
abstract = "Dependency parsing aims to extract syntactic dependency structure or semantic dependency structure for sentences. Existing methods for dependency parsing include transition-based method, graph-based method and sequence-to-sequence method. These methods obtain excellent performance and we notice them belong to labeling method. Therefore, it may be very valuable and interesting to explore the possibility of using generative method to implement dependency parsing. In this paper, we propose to achieve Dependency Parsing (DP) via Sequence Generation (SG) by utilizing only the pre-trained language model without any auxiliary structures. We first explore different serialization designing strategies for converting parsing structures into sequences. Then we design dependency units and concatenate these units into the sequence for DPSG.We verify the DPSG is capable of parsing on widely used DP benchmarks, i.e., PTB, UD2.2, SDP15 and SemEval16.In addition, we also investigate the astonishing low-resource applicability of DPSG, which includes unsupervised cross-domain conducted on CODT and few-shot cross-task conducted on SDP15.Our research demonstrates that sequence generation is one of the effective methods to achieve dependency parsing. Our codes are available now.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2022-dependency">
<titleInfo>
<title>Dependency Parsing via Sequence Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boda</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijun</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shulin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binghao</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Si</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juanzi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dependency parsing aims to extract syntactic dependency structure or semantic dependency structure for sentences. Existing methods for dependency parsing include transition-based method, graph-based method and sequence-to-sequence method. These methods obtain excellent performance and we notice them belong to labeling method. Therefore, it may be very valuable and interesting to explore the possibility of using generative method to implement dependency parsing. In this paper, we propose to achieve Dependency Parsing (DP) via Sequence Generation (SG) by utilizing only the pre-trained language model without any auxiliary structures. We first explore different serialization designing strategies for converting parsing structures into sequences. Then we design dependency units and concatenate these units into the sequence for DPSG.We verify the DPSG is capable of parsing on widely used DP benchmarks, i.e., PTB, UD2.2, SDP15 and SemEval16.In addition, we also investigate the astonishing low-resource applicability of DPSG, which includes unsupervised cross-domain conducted on CODT and few-shot cross-task conducted on SDP15.Our research demonstrates that sequence generation is one of the effective methods to achieve dependency parsing. Our codes are available now.</abstract>
<identifier type="citekey">lin-etal-2022-dependency</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.543</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.543</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7339</start>
<end>7353</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dependency Parsing via Sequence Generation
%A Lin, Boda
%A Yao, Zijun
%A Shi, Jiaxin
%A Cao, Shulin
%A Tang, Binghao
%A Li, Si
%A Luo, Yong
%A Li, Juanzi
%A Hou, Lei
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F lin-etal-2022-dependency
%X Dependency parsing aims to extract syntactic dependency structure or semantic dependency structure for sentences. Existing methods for dependency parsing include transition-based method, graph-based method and sequence-to-sequence method. These methods obtain excellent performance and we notice them belong to labeling method. Therefore, it may be very valuable and interesting to explore the possibility of using generative method to implement dependency parsing. In this paper, we propose to achieve Dependency Parsing (DP) via Sequence Generation (SG) by utilizing only the pre-trained language model without any auxiliary structures. We first explore different serialization designing strategies for converting parsing structures into sequences. Then we design dependency units and concatenate these units into the sequence for DPSG.We verify the DPSG is capable of parsing on widely used DP benchmarks, i.e., PTB, UD2.2, SDP15 and SemEval16.In addition, we also investigate the astonishing low-resource applicability of DPSG, which includes unsupervised cross-domain conducted on CODT and few-shot cross-task conducted on SDP15.Our research demonstrates that sequence generation is one of the effective methods to achieve dependency parsing. Our codes are available now.
%R 10.18653/v1/2022.findings-emnlp.543
%U https://aclanthology.org/2022.findings-emnlp.543
%U https://doi.org/10.18653/v1/2022.findings-emnlp.543
%P 7339-7353
Markdown (Informal)
[Dependency Parsing via Sequence Generation](https://aclanthology.org/2022.findings-emnlp.543) (Lin et al., Findings 2022)
ACL
- Boda Lin, Zijun Yao, Jiaxin Shi, Shulin Cao, Binghao Tang, Si Li, Yong Luo, Juanzi Li, and Lei Hou. 2022. Dependency Parsing via Sequence Generation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 7339–7353, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.