@inproceedings{kann-etal-2019-neural,
title = "Neural Unsupervised Parsing Beyond {E}nglish",
author = "Kann, Katharina and
Mohananey, Anhad and
Bowman, Samuel R. and
Cho, Kyunghyun",
editor = "Cherry, Colin and
Durrett, Greg and
Foster, George and
Haffari, Reza and
Khadivi, Shahram and
Peng, Nanyun and
Ren, Xiang and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6123",
doi = "10.18653/v1/D19-6123",
pages = "209--218",
abstract = "Recently, neural network models which automatically infer syntactic structure from raw text have started to achieve promising results. However, earlier work on unsupervised parsing shows large performance differences between non-neural models trained on corpora in different languages, even for comparable amounts of data. With that in mind, we train instances of the PRPN architecture (Shen et al., 2018){---}one of these unsupervised neural network parsers{---}for Arabic, Chinese, English, and German. We find that (i) the model strongly outperforms trivial baselines and, thus, acquires at least some parsing ability for all languages; (ii) good hyperparameter values seem to be universal; (iii) how the model benefits from larger training set sizes depends on the corpus, with the model achieving the largest performance gains when increasing the number of sentences from 2,500 to 12,500 for English. In addition, we show that, by sharing parameters between the related languages German and English, we can improve the model{'}s unsupervised parsing F1 score by up to 4{\%} in the low-resource setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kann-etal-2019-neural">
<titleInfo>
<title>Neural Unsupervised Parsing Beyond English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anhad</namePart>
<namePart type="family">Mohananey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Bowman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, neural network models which automatically infer syntactic structure from raw text have started to achieve promising results. However, earlier work on unsupervised parsing shows large performance differences between non-neural models trained on corpora in different languages, even for comparable amounts of data. With that in mind, we train instances of the PRPN architecture (Shen et al., 2018)—one of these unsupervised neural network parsers—for Arabic, Chinese, English, and German. We find that (i) the model strongly outperforms trivial baselines and, thus, acquires at least some parsing ability for all languages; (ii) good hyperparameter values seem to be universal; (iii) how the model benefits from larger training set sizes depends on the corpus, with the model achieving the largest performance gains when increasing the number of sentences from 2,500 to 12,500 for English. In addition, we show that, by sharing parameters between the related languages German and English, we can improve the model’s unsupervised parsing F1 score by up to 4% in the low-resource setting.</abstract>
<identifier type="citekey">kann-etal-2019-neural</identifier>
<identifier type="doi">10.18653/v1/D19-6123</identifier>
<location>
<url>https://aclanthology.org/D19-6123</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>209</start>
<end>218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Unsupervised Parsing Beyond English
%A Kann, Katharina
%A Mohananey, Anhad
%A Bowman, Samuel R.
%A Cho, Kyunghyun
%Y Cherry, Colin
%Y Durrett, Greg
%Y Foster, George
%Y Haffari, Reza
%Y Khadivi, Shahram
%Y Peng, Nanyun
%Y Ren, Xiang
%Y Swayamdipta, Swabha
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F kann-etal-2019-neural
%X Recently, neural network models which automatically infer syntactic structure from raw text have started to achieve promising results. However, earlier work on unsupervised parsing shows large performance differences between non-neural models trained on corpora in different languages, even for comparable amounts of data. With that in mind, we train instances of the PRPN architecture (Shen et al., 2018)—one of these unsupervised neural network parsers—for Arabic, Chinese, English, and German. We find that (i) the model strongly outperforms trivial baselines and, thus, acquires at least some parsing ability for all languages; (ii) good hyperparameter values seem to be universal; (iii) how the model benefits from larger training set sizes depends on the corpus, with the model achieving the largest performance gains when increasing the number of sentences from 2,500 to 12,500 for English. In addition, we show that, by sharing parameters between the related languages German and English, we can improve the model’s unsupervised parsing F1 score by up to 4% in the low-resource setting.
%R 10.18653/v1/D19-6123
%U https://aclanthology.org/D19-6123
%U https://doi.org/10.18653/v1/D19-6123
%P 209-218
Markdown (Informal)
[Neural Unsupervised Parsing Beyond English](https://aclanthology.org/D19-6123) (Kann et al., 2019)
ACL
- Katharina Kann, Anhad Mohananey, Samuel R. Bowman, and Kyunghyun Cho. 2019. Neural Unsupervised Parsing Beyond English. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 209–218, Hong Kong, China. Association for Computational Linguistics.