@inproceedings{shen-etal-2022-unsupervised,
title = "Unsupervised Dependency Graph Network",
author = "Shen, Yikang and
Tan, Shawn and
Sordoni, Alessandro and
Li, Peng and
Zhou, Jie and
Courville, Aaron",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.327",
doi = "10.18653/v1/2022.acl-long.327",
pages = "4767--4784",
abstract = "Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, some self-attention heads correspond well to individual dependency types. Inspired by these developments, we propose a new competitive mechanism that encourages these attention heads to model different dependency relations. We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task. Experiment results show that UDGN achieves very strong unsupervised dependency parsing performance without gold POS tags and any other external information. The competitive gated heads show a strong correlation with human-annotated dependency types. Furthermore, the UDGN can also achieve competitive performance on masked language modeling and sentence textual similarity tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2022-unsupervised">
<titleInfo>
<title>Unsupervised Dependency Graph Network</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yikang</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shawn</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Sordoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Courville</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, some self-attention heads correspond well to individual dependency types. Inspired by these developments, we propose a new competitive mechanism that encourages these attention heads to model different dependency relations. We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task. Experiment results show that UDGN achieves very strong unsupervised dependency parsing performance without gold POS tags and any other external information. The competitive gated heads show a strong correlation with human-annotated dependency types. Furthermore, the UDGN can also achieve competitive performance on masked language modeling and sentence textual similarity tasks.</abstract>
<identifier type="citekey">shen-etal-2022-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.327</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.327</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>4767</start>
<end>4784</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Dependency Graph Network
%A Shen, Yikang
%A Tan, Shawn
%A Sordoni, Alessandro
%A Li, Peng
%A Zhou, Jie
%A Courville, Aaron
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F shen-etal-2022-unsupervised
%X Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, some self-attention heads correspond well to individual dependency types. Inspired by these developments, we propose a new competitive mechanism that encourages these attention heads to model different dependency relations. We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task. Experiment results show that UDGN achieves very strong unsupervised dependency parsing performance without gold POS tags and any other external information. The competitive gated heads show a strong correlation with human-annotated dependency types. Furthermore, the UDGN can also achieve competitive performance on masked language modeling and sentence textual similarity tasks.
%R 10.18653/v1/2022.acl-long.327
%U https://aclanthology.org/2022.acl-long.327
%U https://doi.org/10.18653/v1/2022.acl-long.327
%P 4767-4784
Markdown (Informal)
[Unsupervised Dependency Graph Network](https://aclanthology.org/2022.acl-long.327) (Shen et al., ACL 2022)
ACL
- Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li, Jie Zhou, and Aaron Courville. 2022. Unsupervised Dependency Graph Network. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4767–4784, Dublin, Ireland. Association for Computational Linguistics.