@inproceedings{varada-etal-2020-using,
title = "Using Alternate Representations of Text for Natural Language Understanding",
author = "Varada, Venkat and
Peris, Charith and
Park, Yangsook and
Dipersio, Christopher",
editor = "Wen, Tsung-Hsien and
Celikyilmaz, Asli and
Yu, Zhou and
Papangelis, Alexandros and
Eric, Mihail and
Kumar, Anuj and
Casanueva, I{\~n}igo and
Shah, Rushin",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlp4convai-1.1",
doi = "10.18653/v1/2020.nlp4convai-1.1",
pages = "1--10",
abstract = "One of the core components of voice assistants is the Natural Language Understanding (NLU) model. Its ability to accurately classify the user{'}s request (or {``}intent{''}) and recognize named entities in an utterance is pivotal to the success of these assistants. NLU models can be challenged in some languages by code-switching or morphological and orthographic variations. This work explores the possibility of improving the accuracy of NLU models for Indic languages via the use of alternate representations of input text for NLU, specifically ISO-15919 and IndicSOUNDEX, a custom SOUNDEX designed to work for Indic languages. We used a deep neural network based model to incorporate the information from alternate representations into the NLU model. We show that using alternate representations significantly improves the overall performance of NLU models when training data is limited.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varada-etal-2020-using">
<titleInfo>
<title>Using Alternate Representations of Text for Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Venkat</namePart>
<namePart type="family">Varada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charith</namePart>
<namePart type="family">Peris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangsook</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Dipersio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihail</namePart>
<namePart type="family">Eric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñigo</namePart>
<namePart type="family">Casanueva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rushin</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One of the core components of voice assistants is the Natural Language Understanding (NLU) model. Its ability to accurately classify the user’s request (or “intent”) and recognize named entities in an utterance is pivotal to the success of these assistants. NLU models can be challenged in some languages by code-switching or morphological and orthographic variations. This work explores the possibility of improving the accuracy of NLU models for Indic languages via the use of alternate representations of input text for NLU, specifically ISO-15919 and IndicSOUNDEX, a custom SOUNDEX designed to work for Indic languages. We used a deep neural network based model to incorporate the information from alternate representations into the NLU model. We show that using alternate representations significantly improves the overall performance of NLU models when training data is limited.</abstract>
<identifier type="citekey">varada-etal-2020-using</identifier>
<identifier type="doi">10.18653/v1/2020.nlp4convai-1.1</identifier>
<location>
<url>https://aclanthology.org/2020.nlp4convai-1.1</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Alternate Representations of Text for Natural Language Understanding
%A Varada, Venkat
%A Peris, Charith
%A Park, Yangsook
%A Dipersio, Christopher
%Y Wen, Tsung-Hsien
%Y Celikyilmaz, Asli
%Y Yu, Zhou
%Y Papangelis, Alexandros
%Y Eric, Mihail
%Y Kumar, Anuj
%Y Casanueva, Iñigo
%Y Shah, Rushin
%S Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F varada-etal-2020-using
%X One of the core components of voice assistants is the Natural Language Understanding (NLU) model. Its ability to accurately classify the user’s request (or “intent”) and recognize named entities in an utterance is pivotal to the success of these assistants. NLU models can be challenged in some languages by code-switching or morphological and orthographic variations. This work explores the possibility of improving the accuracy of NLU models for Indic languages via the use of alternate representations of input text for NLU, specifically ISO-15919 and IndicSOUNDEX, a custom SOUNDEX designed to work for Indic languages. We used a deep neural network based model to incorporate the information from alternate representations into the NLU model. We show that using alternate representations significantly improves the overall performance of NLU models when training data is limited.
%R 10.18653/v1/2020.nlp4convai-1.1
%U https://aclanthology.org/2020.nlp4convai-1.1
%U https://doi.org/10.18653/v1/2020.nlp4convai-1.1
%P 1-10
Markdown (Informal)
[Using Alternate Representations of Text for Natural Language Understanding](https://aclanthology.org/2020.nlp4convai-1.1) (Varada et al., NLP4ConvAI 2020)
ACL