@inproceedings{ryskina-etal-2021-comparative,
title = "Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction",
author = "Ryskina, Maria and
Hovy, Eduard and
Berg-Kirkpatrick, Taylor and
Gormley, Matthew R.",
editor = "Nicolai, Garrett and
Gorman, Kyle and
Cotterell, Ryan",
booktitle = "Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigmorphon-1.22",
doi = "10.18653/v1/2021.sigmorphon-1.22",
pages = "198--211",
abstract = "Traditionally, character-level transduction problems have been solved with finite-state models designed to encode structural and linguistic knowledge of the underlying process, whereas recent approaches rely on the power and flexibility of sequence-to-sequence models with attention. Focusing on the less explored unsupervised learning scenario, we compare the two model classes side by side and find that they tend to make different types of errors even when achieving comparable performance. We analyze the distributions of different error classes using two unsupervised tasks as testbeds: converting informally romanized text into the native script of its language (for Russian, Arabic, and Kannada) and translating between a pair of closely related languages (Serbian and Bosnian). Finally, we investigate how combining finite-state and sequence-to-sequence models at decoding time affects the output quantitatively and qualitatively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ryskina-etal-2021-comparative">
<titleInfo>
<title>Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Ryskina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taylor</namePart>
<namePart type="family">Berg-Kirkpatrick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Gormley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Gorman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</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>Traditionally, character-level transduction problems have been solved with finite-state models designed to encode structural and linguistic knowledge of the underlying process, whereas recent approaches rely on the power and flexibility of sequence-to-sequence models with attention. Focusing on the less explored unsupervised learning scenario, we compare the two model classes side by side and find that they tend to make different types of errors even when achieving comparable performance. We analyze the distributions of different error classes using two unsupervised tasks as testbeds: converting informally romanized text into the native script of its language (for Russian, Arabic, and Kannada) and translating between a pair of closely related languages (Serbian and Bosnian). Finally, we investigate how combining finite-state and sequence-to-sequence models at decoding time affects the output quantitatively and qualitatively.</abstract>
<identifier type="citekey">ryskina-etal-2021-comparative</identifier>
<identifier type="doi">10.18653/v1/2021.sigmorphon-1.22</identifier>
<location>
<url>https://aclanthology.org/2021.sigmorphon-1.22</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>198</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction
%A Ryskina, Maria
%A Hovy, Eduard
%A Berg-Kirkpatrick, Taylor
%A Gormley, Matthew R.
%Y Nicolai, Garrett
%Y Gorman, Kyle
%Y Cotterell, Ryan
%S Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F ryskina-etal-2021-comparative
%X Traditionally, character-level transduction problems have been solved with finite-state models designed to encode structural and linguistic knowledge of the underlying process, whereas recent approaches rely on the power and flexibility of sequence-to-sequence models with attention. Focusing on the less explored unsupervised learning scenario, we compare the two model classes side by side and find that they tend to make different types of errors even when achieving comparable performance. We analyze the distributions of different error classes using two unsupervised tasks as testbeds: converting informally romanized text into the native script of its language (for Russian, Arabic, and Kannada) and translating between a pair of closely related languages (Serbian and Bosnian). Finally, we investigate how combining finite-state and sequence-to-sequence models at decoding time affects the output quantitatively and qualitatively.
%R 10.18653/v1/2021.sigmorphon-1.22
%U https://aclanthology.org/2021.sigmorphon-1.22
%U https://doi.org/10.18653/v1/2021.sigmorphon-1.22
%P 198-211
Markdown (Informal)
[Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction](https://aclanthology.org/2021.sigmorphon-1.22) (Ryskina et al., SIGMORPHON 2021)
ACL