@inproceedings{mansfield-etal-2019-neural,
title = "Neural Text Normalization with Subword Units",
author = {Mansfield, Courtney and
Sun, Ming and
Liu, Yuzong and
Gandhe, Ankur and
Hoffmeister, Bj{\"o}rn},
editor = "Loukina, Anastassia and
Morales, Michelle and
Kumar, Rohit",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-2024",
doi = "10.18653/v1/N19-2024",
pages = "190--196",
abstract = "Text normalization (TN) is an important step in conversational systems. It converts written text to its spoken form to facilitate speech recognition, natural language understanding and text-to-speech synthesis. Finite state transducers (FSTs) are commonly used to build grammars that handle text normalization. However, translating linguistic knowledge into grammars requires extensive effort. In this paper, we frame TN as a machine translation task and tackle it with sequence-to-sequence (seq2seq) models. Previous research focuses on normalizing a word (or phrase) with the help of limited word-level context, while our approach directly normalizes full sentences. We find subword models with additional linguistic features yield the best performance (with a word error rate of 0.17{\%}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mansfield-etal-2019-neural">
<titleInfo>
<title>Neural Text Normalization with Subword Units</title>
</titleInfo>
<name type="personal">
<namePart type="given">Courtney</namePart>
<namePart type="family">Mansfield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuzong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankur</namePart>
<namePart type="family">Gandhe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Björn</namePart>
<namePart type="family">Hoffmeister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastassia</namePart>
<namePart type="family">Loukina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michelle</namePart>
<namePart type="family">Morales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text normalization (TN) is an important step in conversational systems. It converts written text to its spoken form to facilitate speech recognition, natural language understanding and text-to-speech synthesis. Finite state transducers (FSTs) are commonly used to build grammars that handle text normalization. However, translating linguistic knowledge into grammars requires extensive effort. In this paper, we frame TN as a machine translation task and tackle it with sequence-to-sequence (seq2seq) models. Previous research focuses on normalizing a word (or phrase) with the help of limited word-level context, while our approach directly normalizes full sentences. We find subword models with additional linguistic features yield the best performance (with a word error rate of 0.17%).</abstract>
<identifier type="citekey">mansfield-etal-2019-neural</identifier>
<identifier type="doi">10.18653/v1/N19-2024</identifier>
<location>
<url>https://aclanthology.org/N19-2024</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>190</start>
<end>196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Text Normalization with Subword Units
%A Mansfield, Courtney
%A Sun, Ming
%A Liu, Yuzong
%A Gandhe, Ankur
%A Hoffmeister, Björn
%Y Loukina, Anastassia
%Y Morales, Michelle
%Y Kumar, Rohit
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F mansfield-etal-2019-neural
%X Text normalization (TN) is an important step in conversational systems. It converts written text to its spoken form to facilitate speech recognition, natural language understanding and text-to-speech synthesis. Finite state transducers (FSTs) are commonly used to build grammars that handle text normalization. However, translating linguistic knowledge into grammars requires extensive effort. In this paper, we frame TN as a machine translation task and tackle it with sequence-to-sequence (seq2seq) models. Previous research focuses on normalizing a word (or phrase) with the help of limited word-level context, while our approach directly normalizes full sentences. We find subword models with additional linguistic features yield the best performance (with a word error rate of 0.17%).
%R 10.18653/v1/N19-2024
%U https://aclanthology.org/N19-2024
%U https://doi.org/10.18653/v1/N19-2024
%P 190-196
Markdown (Informal)
[Neural Text Normalization with Subword Units](https://aclanthology.org/N19-2024) (Mansfield et al., NAACL 2019)
ACL
- Courtney Mansfield, Ming Sun, Yuzong Liu, Ankur Gandhe, and Björn Hoffmeister. 2019. Neural Text Normalization with Subword Units. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers), pages 190–196, Minneapolis, Minnesota. Association for Computational Linguistics.