@inproceedings{kipyatkova-karpov-2020-class,
title = "Class-based {LSTM} {R}ussian Language Model with Linguistic Information",
author = "Kipyatkova, Irina and
Karpov, Alexey",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.300",
pages = "2470--2474",
abstract = "In the paper, we present class-based LSTM Russian language models (LMs) with classes generated with the use of both word frequency and linguistic information data, obtained with the help of the {``}VisualSynan{''} software from the AOT project. We have created LSTM LMs with various numbers of classes and compared them with word-based LM and class-based LM with word2vec class generation in terms of perplexity, training time, and WER. In addition, we performed a linear interpolation of LSTM language models with the baseline 3-gram language model. The LSTM language models were used for very large vocabulary continuous Russian speech recognition at an N-best list rescoring stage. We achieved significant progress in training time reduction with only slight degradation in recognition accuracy comparing to the word-based LM. In addition, our LM with classes generated using linguistic information outperformed LM with classes generated using word2vec. We achieved WER of 14.94 {\%} at our own speech corpus of continuous Russian speech that is 15 {\%} relative reduction with respect to the baseline 3-gram model.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kipyatkova-karpov-2020-class">
<titleInfo>
<title>Class-based LSTM Russian Language Model with Linguistic Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Kipyatkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Karpov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In the paper, we present class-based LSTM Russian language models (LMs) with classes generated with the use of both word frequency and linguistic information data, obtained with the help of the “VisualSynan” software from the AOT project. We have created LSTM LMs with various numbers of classes and compared them with word-based LM and class-based LM with word2vec class generation in terms of perplexity, training time, and WER. In addition, we performed a linear interpolation of LSTM language models with the baseline 3-gram language model. The LSTM language models were used for very large vocabulary continuous Russian speech recognition at an N-best list rescoring stage. We achieved significant progress in training time reduction with only slight degradation in recognition accuracy comparing to the word-based LM. In addition, our LM with classes generated using linguistic information outperformed LM with classes generated using word2vec. We achieved WER of 14.94 % at our own speech corpus of continuous Russian speech that is 15 % relative reduction with respect to the baseline 3-gram model.</abstract>
<identifier type="citekey">kipyatkova-karpov-2020-class</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.300</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>2470</start>
<end>2474</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Class-based LSTM Russian Language Model with Linguistic Information
%A Kipyatkova, Irina
%A Karpov, Alexey
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F kipyatkova-karpov-2020-class
%X In the paper, we present class-based LSTM Russian language models (LMs) with classes generated with the use of both word frequency and linguistic information data, obtained with the help of the “VisualSynan” software from the AOT project. We have created LSTM LMs with various numbers of classes and compared them with word-based LM and class-based LM with word2vec class generation in terms of perplexity, training time, and WER. In addition, we performed a linear interpolation of LSTM language models with the baseline 3-gram language model. The LSTM language models were used for very large vocabulary continuous Russian speech recognition at an N-best list rescoring stage. We achieved significant progress in training time reduction with only slight degradation in recognition accuracy comparing to the word-based LM. In addition, our LM with classes generated using linguistic information outperformed LM with classes generated using word2vec. We achieved WER of 14.94 % at our own speech corpus of continuous Russian speech that is 15 % relative reduction with respect to the baseline 3-gram model.
%U https://aclanthology.org/2020.lrec-1.300
%P 2470-2474
Markdown (Informal)
[Class-based LSTM Russian Language Model with Linguistic Information](https://aclanthology.org/2020.lrec-1.300) (Kipyatkova & Karpov, LREC 2020)
ACL