@inproceedings{kaing-etal-2021-multi,
title = "Multi-Source Cross-Lingual Constituency Parsing",
author = "Kaing, Hour and
Ding, Chenchen and
Sudoh, Katsuhito and
Utiyama, Masao and
Sumita, Eiichiro and
Nakamura, Satoshi",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.41",
pages = "341--346",
abstract = "Pretrained multilingual language models have become a key part of cross-lingual transfer for many natural language processing tasks, even those without bilingual information. This work further investigates the cross-lingual transfer ability of these models for constituency parsing and focuses on multi-source transfer. Addressing structure and label set diversity problems, we propose the integration of typological features into the parsing model and treebank normalization. We trained the model on eight languages with diverse structures and use transfer parsing for an additional six low-resource languages. The experimental results show that the treebank normalization is essential for cross-lingual transfer performance and the typological features introduce further improvement. As a result, our approach improves the baseline F1 of multi-source transfer by 5 on average.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaing-etal-2021-multi">
<titleInfo>
<title>Multi-Source Cross-Lingual Constituency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hour</namePart>
<namePart type="family">Kaing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenchen</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pretrained multilingual language models have become a key part of cross-lingual transfer for many natural language processing tasks, even those without bilingual information. This work further investigates the cross-lingual transfer ability of these models for constituency parsing and focuses on multi-source transfer. Addressing structure and label set diversity problems, we propose the integration of typological features into the parsing model and treebank normalization. We trained the model on eight languages with diverse structures and use transfer parsing for an additional six low-resource languages. The experimental results show that the treebank normalization is essential for cross-lingual transfer performance and the typological features introduce further improvement. As a result, our approach improves the baseline F1 of multi-source transfer by 5 on average.</abstract>
<identifier type="citekey">kaing-etal-2021-multi</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.41</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>341</start>
<end>346</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Source Cross-Lingual Constituency Parsing
%A Kaing, Hour
%A Ding, Chenchen
%A Sudoh, Katsuhito
%A Utiyama, Masao
%A Sumita, Eiichiro
%A Nakamura, Satoshi
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F kaing-etal-2021-multi
%X Pretrained multilingual language models have become a key part of cross-lingual transfer for many natural language processing tasks, even those without bilingual information. This work further investigates the cross-lingual transfer ability of these models for constituency parsing and focuses on multi-source transfer. Addressing structure and label set diversity problems, we propose the integration of typological features into the parsing model and treebank normalization. We trained the model on eight languages with diverse structures and use transfer parsing for an additional six low-resource languages. The experimental results show that the treebank normalization is essential for cross-lingual transfer performance and the typological features introduce further improvement. As a result, our approach improves the baseline F1 of multi-source transfer by 5 on average.
%U https://aclanthology.org/2021.icon-main.41
%P 341-346
Markdown (Informal)
[Multi-Source Cross-Lingual Constituency Parsing](https://aclanthology.org/2021.icon-main.41) (Kaing et al., ICON 2021)
ACL
- Hour Kaing, Chenchen Ding, Katsuhito Sudoh, Masao Utiyama, Eiichiro Sumita, and Satoshi Nakamura. 2021. Multi-Source Cross-Lingual Constituency Parsing. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 341–346, National Institute of Technology Silchar, Silchar, India. NLP Association of India (NLPAI).