@inproceedings{kim-etal-2021-multilingual-chart-based,
title = "Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models",
author = "Kim, Taeuk and
Li, Bowen and
Lee, Sang-goo",
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.41",
doi = "10.18653/v1/2021.findings-emnlp.41",
pages = "454--463",
abstract = "As it has been unveiled that pre-trained language models (PLMs) are to some extent capable of recognizing syntactic concepts in natural language, much effort has been made to develop a method for extracting complete (binary) parses from PLMs without training separate parsers. We improve upon this paradigm by proposing a novel chart-based method and an effective top-K ensemble technique. Moreover, we demonstrate that we can broaden the scope of application of the approach into multilingual settings. Specifically, we show that by applying our method on multilingual PLMs, it becomes possible to induce non-trivial parses for sentences from nine languages in an integrated and language-agnostic manner, attaining performance superior or comparable to that of unsupervised PCFGs. We also verify that our approach is robust to cross-lingual transfer. Finally, we provide analyses on the inner workings of our method. For instance, we discover universal attention heads which are consistently sensitive to syntactic information irrespective of the input language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2021-multilingual-chart-based">
<titleInfo>
<title>Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taeuk</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sang-goo</namePart>
<namePart type="family">Lee</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>As it has been unveiled that pre-trained language models (PLMs) are to some extent capable of recognizing syntactic concepts in natural language, much effort has been made to develop a method for extracting complete (binary) parses from PLMs without training separate parsers. We improve upon this paradigm by proposing a novel chart-based method and an effective top-K ensemble technique. Moreover, we demonstrate that we can broaden the scope of application of the approach into multilingual settings. Specifically, we show that by applying our method on multilingual PLMs, it becomes possible to induce non-trivial parses for sentences from nine languages in an integrated and language-agnostic manner, attaining performance superior or comparable to that of unsupervised PCFGs. We also verify that our approach is robust to cross-lingual transfer. Finally, we provide analyses on the inner workings of our method. For instance, we discover universal attention heads which are consistently sensitive to syntactic information irrespective of the input language.</abstract>
<identifier type="citekey">kim-etal-2021-multilingual-chart-based</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.41</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.41</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>454</start>
<end>463</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models
%A Kim, Taeuk
%A Li, Bowen
%A Lee, Sang-goo
%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 kim-etal-2021-multilingual-chart-based
%X As it has been unveiled that pre-trained language models (PLMs) are to some extent capable of recognizing syntactic concepts in natural language, much effort has been made to develop a method for extracting complete (binary) parses from PLMs without training separate parsers. We improve upon this paradigm by proposing a novel chart-based method and an effective top-K ensemble technique. Moreover, we demonstrate that we can broaden the scope of application of the approach into multilingual settings. Specifically, we show that by applying our method on multilingual PLMs, it becomes possible to induce non-trivial parses for sentences from nine languages in an integrated and language-agnostic manner, attaining performance superior or comparable to that of unsupervised PCFGs. We also verify that our approach is robust to cross-lingual transfer. Finally, we provide analyses on the inner workings of our method. For instance, we discover universal attention heads which are consistently sensitive to syntactic information irrespective of the input language.
%R 10.18653/v1/2021.findings-emnlp.41
%U https://aclanthology.org/2021.findings-emnlp.41
%U https://doi.org/10.18653/v1/2021.findings-emnlp.41
%P 454-463
Markdown (Informal)
[Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models](https://aclanthology.org/2021.findings-emnlp.41) (Kim et al., Findings 2021)
ACL