@inproceedings{skachkova-etal-2018-closing,
title = "Closing Brackets with Recurrent Neural Networks",
author = "Skachkova, Natalia and
Trost, Thomas and
Klakow, Dietrich",
editor = "Linzen, Tal and
Chrupa{\l}a, Grzegorz and
Alishahi, Afra",
booktitle = "Proceedings of the 2018 {EMNLP} Workshop {B}lackbox{NLP}: Analyzing and Interpreting Neural Networks for {NLP}",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5425",
doi = "10.18653/v1/W18-5425",
pages = "232--239",
abstract = "Many natural and formal languages contain words or symbols that require a matching counterpart for making an expression well-formed. The combination of opening and closing brackets is a typical example of such a construction. Due to their commonness, the ability to follow such rules is important for language modeling. Currently, recurrent neural networks (RNNs) are extensively used for this task. We investigate whether they are capable of learning the rules of opening and closing brackets by applying them to synthetic Dyck languages that consist of different types of brackets. We provide an analysis of the statistical properties of these languages as a baseline and show strengths and limits of Elman-RNNs, GRUs and LSTMs in experiments on random samples of these languages. In terms of perplexity and prediction accuracy, the RNNs get close to the theoretical baseline in most cases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skachkova-etal-2018-closing">
<titleInfo>
<title>Closing Brackets with Recurrent Neural Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Skachkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Trost</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grzegorz</namePart>
<namePart type="family">Chrupała</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afra</namePart>
<namePart type="family">Alishahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many natural and formal languages contain words or symbols that require a matching counterpart for making an expression well-formed. The combination of opening and closing brackets is a typical example of such a construction. Due to their commonness, the ability to follow such rules is important for language modeling. Currently, recurrent neural networks (RNNs) are extensively used for this task. We investigate whether they are capable of learning the rules of opening and closing brackets by applying them to synthetic Dyck languages that consist of different types of brackets. We provide an analysis of the statistical properties of these languages as a baseline and show strengths and limits of Elman-RNNs, GRUs and LSTMs in experiments on random samples of these languages. In terms of perplexity and prediction accuracy, the RNNs get close to the theoretical baseline in most cases.</abstract>
<identifier type="citekey">skachkova-etal-2018-closing</identifier>
<identifier type="doi">10.18653/v1/W18-5425</identifier>
<location>
<url>https://aclanthology.org/W18-5425</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>232</start>
<end>239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Closing Brackets with Recurrent Neural Networks
%A Skachkova, Natalia
%A Trost, Thomas
%A Klakow, Dietrich
%Y Linzen, Tal
%Y Chrupała, Grzegorz
%Y Alishahi, Afra
%S Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F skachkova-etal-2018-closing
%X Many natural and formal languages contain words or symbols that require a matching counterpart for making an expression well-formed. The combination of opening and closing brackets is a typical example of such a construction. Due to their commonness, the ability to follow such rules is important for language modeling. Currently, recurrent neural networks (RNNs) are extensively used for this task. We investigate whether they are capable of learning the rules of opening and closing brackets by applying them to synthetic Dyck languages that consist of different types of brackets. We provide an analysis of the statistical properties of these languages as a baseline and show strengths and limits of Elman-RNNs, GRUs and LSTMs in experiments on random samples of these languages. In terms of perplexity and prediction accuracy, the RNNs get close to the theoretical baseline in most cases.
%R 10.18653/v1/W18-5425
%U https://aclanthology.org/W18-5425
%U https://doi.org/10.18653/v1/W18-5425
%P 232-239
Markdown (Informal)
[Closing Brackets with Recurrent Neural Networks](https://aclanthology.org/W18-5425) (Skachkova et al., EMNLP 2018)
ACL
- Natalia Skachkova, Thomas Trost, and Dietrich Klakow. 2018. Closing Brackets with Recurrent Neural Networks. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 232–239, Brussels, Belgium. Association for Computational Linguistics.