@inproceedings{li-etal-2020-semi,
title = "Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations",
author = "Li, Ying and
Li, Zhenghua and
Zhang, Min",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.338",
doi = "10.18653/v1/2020.coling-main.338",
pages = "3806--3817",
abstract = "In recent years, parsing performance is dramatically improved on in-domain texts thanks to the rapid progress of deep neural network models. The major challenge for current parsing research is to improve parsing performance on out-of-domain texts that are very different from the in-domain training data when there is only a small-scale out-domain labeled data. To deal with this problem, we propose to improve the contextualized word representations via adversarial learning and fine-tuning BERT processes. Concretely, we apply adversarial learning to three representative semi-supervised domain adaption methods, i.e., direct concatenation (CON), feature augmentation (FA), and domain embedding (DE) with two useful strategies, i.e., fused target-domain word representations and orthogonality constraints, thus enabling to model more pure yet effective domain-specific and domain-invariant representations. Simultaneously, we utilize a large-scale target-domain unlabeled data to fine-tune BERT with only the language model loss, thus obtaining reliable contextualized word representations that benefit for the cross-domain dependency parsing. Experiments on a benchmark dataset show that our proposed adversarial approaches achieve consistent improvement, and fine-tuning BERT further boosts parsing accuracy by a large margin. Our single model achieves the same state-of-the-art performance as the top submitted system in the NLPCC-2019 shared task, which uses ensemble models and BERT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-semi">
<titleInfo>
<title>Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenghua</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, parsing performance is dramatically improved on in-domain texts thanks to the rapid progress of deep neural network models. The major challenge for current parsing research is to improve parsing performance on out-of-domain texts that are very different from the in-domain training data when there is only a small-scale out-domain labeled data. To deal with this problem, we propose to improve the contextualized word representations via adversarial learning and fine-tuning BERT processes. Concretely, we apply adversarial learning to three representative semi-supervised domain adaption methods, i.e., direct concatenation (CON), feature augmentation (FA), and domain embedding (DE) with two useful strategies, i.e., fused target-domain word representations and orthogonality constraints, thus enabling to model more pure yet effective domain-specific and domain-invariant representations. Simultaneously, we utilize a large-scale target-domain unlabeled data to fine-tune BERT with only the language model loss, thus obtaining reliable contextualized word representations that benefit for the cross-domain dependency parsing. Experiments on a benchmark dataset show that our proposed adversarial approaches achieve consistent improvement, and fine-tuning BERT further boosts parsing accuracy by a large margin. Our single model achieves the same state-of-the-art performance as the top submitted system in the NLPCC-2019 shared task, which uses ensemble models and BERT.</abstract>
<identifier type="citekey">li-etal-2020-semi</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.338</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.338</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>3806</start>
<end>3817</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations
%A Li, Ying
%A Li, Zhenghua
%A Zhang, Min
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F li-etal-2020-semi
%X In recent years, parsing performance is dramatically improved on in-domain texts thanks to the rapid progress of deep neural network models. The major challenge for current parsing research is to improve parsing performance on out-of-domain texts that are very different from the in-domain training data when there is only a small-scale out-domain labeled data. To deal with this problem, we propose to improve the contextualized word representations via adversarial learning and fine-tuning BERT processes. Concretely, we apply adversarial learning to three representative semi-supervised domain adaption methods, i.e., direct concatenation (CON), feature augmentation (FA), and domain embedding (DE) with two useful strategies, i.e., fused target-domain word representations and orthogonality constraints, thus enabling to model more pure yet effective domain-specific and domain-invariant representations. Simultaneously, we utilize a large-scale target-domain unlabeled data to fine-tune BERT with only the language model loss, thus obtaining reliable contextualized word representations that benefit for the cross-domain dependency parsing. Experiments on a benchmark dataset show that our proposed adversarial approaches achieve consistent improvement, and fine-tuning BERT further boosts parsing accuracy by a large margin. Our single model achieves the same state-of-the-art performance as the top submitted system in the NLPCC-2019 shared task, which uses ensemble models and BERT.
%R 10.18653/v1/2020.coling-main.338
%U https://aclanthology.org/2020.coling-main.338
%U https://doi.org/10.18653/v1/2020.coling-main.338
%P 3806-3817
Markdown (Informal)
[Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations](https://aclanthology.org/2020.coling-main.338) (Li et al., COLING 2020)
ACL