@inproceedings{wang-tu-2020-semi,
title = "Semi-Supervised Dependency Parsing with Arc-Factored Variational Autoencoding",
author = "Wang, Ge and
Tu, Kewei",
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.224/",
doi = "10.18653/v1/2020.coling-main.224",
pages = "2485--2496",
abstract = "Mannual annotation for dependency parsing is both labourious and time costly, resulting in the difficulty to learn practical dependency parsers for many languages due to the lack of labelled training corpora. To compensate for the scarcity of labelled data, semi-supervised dependency parsing methods are developed to utilize unlabelled data in the training procedure of dependency parsers. In previous work, the autoencoder framework is a prevalent approach for the utilization of unlabelled data. In this framework, training sentences are reconstructed from a decoder conditioned on dependency trees predicted by an encoder. The tree structure requirement brings challenges for both the encoder and the decoder. Sophisticated techniques are employed to tackle these challenges at the expense of model complexity and approximations in encoding and decoding. In this paper, we propose a model based on the variational autoencoder framework. By relaxing the tree constraint in both the encoder and the decoder during training, we make the learning of our model fully arc-factored and thus circumvent the challenges brought by the tree constraint. We evaluate our model on datasets across several languages and the results demonstrate the advantage of our model over previous approaches in both parsing accuracy and speed."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-tu-2020-semi">
<titleInfo>
<title>Semi-Supervised Dependency Parsing with Arc-Factored Variational Autoencoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ge</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kewei</namePart>
<namePart type="family">Tu</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>Mannual annotation for dependency parsing is both labourious and time costly, resulting in the difficulty to learn practical dependency parsers for many languages due to the lack of labelled training corpora. To compensate for the scarcity of labelled data, semi-supervised dependency parsing methods are developed to utilize unlabelled data in the training procedure of dependency parsers. In previous work, the autoencoder framework is a prevalent approach for the utilization of unlabelled data. In this framework, training sentences are reconstructed from a decoder conditioned on dependency trees predicted by an encoder. The tree structure requirement brings challenges for both the encoder and the decoder. Sophisticated techniques are employed to tackle these challenges at the expense of model complexity and approximations in encoding and decoding. In this paper, we propose a model based on the variational autoencoder framework. By relaxing the tree constraint in both the encoder and the decoder during training, we make the learning of our model fully arc-factored and thus circumvent the challenges brought by the tree constraint. We evaluate our model on datasets across several languages and the results demonstrate the advantage of our model over previous approaches in both parsing accuracy and speed.</abstract>
<identifier type="citekey">wang-tu-2020-semi</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.224</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.224/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2485</start>
<end>2496</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-Supervised Dependency Parsing with Arc-Factored Variational Autoencoding
%A Wang, Ge
%A Tu, Kewei
%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 wang-tu-2020-semi
%X Mannual annotation for dependency parsing is both labourious and time costly, resulting in the difficulty to learn practical dependency parsers for many languages due to the lack of labelled training corpora. To compensate for the scarcity of labelled data, semi-supervised dependency parsing methods are developed to utilize unlabelled data in the training procedure of dependency parsers. In previous work, the autoencoder framework is a prevalent approach for the utilization of unlabelled data. In this framework, training sentences are reconstructed from a decoder conditioned on dependency trees predicted by an encoder. The tree structure requirement brings challenges for both the encoder and the decoder. Sophisticated techniques are employed to tackle these challenges at the expense of model complexity and approximations in encoding and decoding. In this paper, we propose a model based on the variational autoencoder framework. By relaxing the tree constraint in both the encoder and the decoder during training, we make the learning of our model fully arc-factored and thus circumvent the challenges brought by the tree constraint. We evaluate our model on datasets across several languages and the results demonstrate the advantage of our model over previous approaches in both parsing accuracy and speed.
%R 10.18653/v1/2020.coling-main.224
%U https://aclanthology.org/2020.coling-main.224/
%U https://doi.org/10.18653/v1/2020.coling-main.224
%P 2485-2496
Markdown (Informal)
[Semi-Supervised Dependency Parsing with Arc-Factored Variational Autoencoding](https://aclanthology.org/2020.coling-main.224/) (Wang & Tu, COLING 2020)
ACL