@inproceedings{wagner-foster-2021-revisiting,
title = "Revisiting Tri-training of Dependency Parsers",
author = "Wagner, Joachim and
Foster, Jennifer",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.745/",
doi = "10.18653/v1/2021.emnlp-main.745",
pages = "9457--9473",
abstract = "We compare two orthogonal semi-supervised learning techniques, namely tri-training and pretrained word embeddings, in the task of dependency parsing. We explore language-specific FastText and ELMo embeddings and multilingual BERT embeddings. We focus on a low resource scenario as semi-supervised learning can be expected to have the most impact here. Based on treebank size and available ELMo models, we select Hungarian, Uyghur (a zero-shot language for mBERT) and Vietnamese. Furthermore, we include English in a simulated low-resource setting. We find that pretrained word embeddings make more effective use of unlabelled data than tri-training but that the two approaches can be successfully combined."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wagner-foster-2021-revisiting">
<titleInfo>
<title>Revisiting Tri-training of Dependency Parsers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Wagner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Foster</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>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</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">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We compare two orthogonal semi-supervised learning techniques, namely tri-training and pretrained word embeddings, in the task of dependency parsing. We explore language-specific FastText and ELMo embeddings and multilingual BERT embeddings. We focus on a low resource scenario as semi-supervised learning can be expected to have the most impact here. Based on treebank size and available ELMo models, we select Hungarian, Uyghur (a zero-shot language for mBERT) and Vietnamese. Furthermore, we include English in a simulated low-resource setting. We find that pretrained word embeddings make more effective use of unlabelled data than tri-training but that the two approaches can be successfully combined.</abstract>
<identifier type="citekey">wagner-foster-2021-revisiting</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.745</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.745/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>9457</start>
<end>9473</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Tri-training of Dependency Parsers
%A Wagner, Joachim
%A Foster, Jennifer
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F wagner-foster-2021-revisiting
%X We compare two orthogonal semi-supervised learning techniques, namely tri-training and pretrained word embeddings, in the task of dependency parsing. We explore language-specific FastText and ELMo embeddings and multilingual BERT embeddings. We focus on a low resource scenario as semi-supervised learning can be expected to have the most impact here. Based on treebank size and available ELMo models, we select Hungarian, Uyghur (a zero-shot language for mBERT) and Vietnamese. Furthermore, we include English in a simulated low-resource setting. We find that pretrained word embeddings make more effective use of unlabelled data than tri-training but that the two approaches can be successfully combined.
%R 10.18653/v1/2021.emnlp-main.745
%U https://aclanthology.org/2021.emnlp-main.745/
%U https://doi.org/10.18653/v1/2021.emnlp-main.745
%P 9457-9473
Markdown (Informal)
[Revisiting Tri-training of Dependency Parsers](https://aclanthology.org/2021.emnlp-main.745/) (Wagner & Foster, EMNLP 2021)
ACL
- Joachim Wagner and Jennifer Foster. 2021. Revisiting Tri-training of Dependency Parsers. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9457–9473, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.