@inproceedings{lin-2023-future,
title = "A future for universal grapheme-phoneme transduction modeling with neuralized finite-state transducers",
author = "Lin, Chu-Cheng Lin",
editor = {Nicolai, Garrett and
Chodroff, Eleanor and
Mailhot, Frederic and
{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
booktitle = "Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigmorphon-1.30",
doi = "10.18653/v1/2023.sigmorphon-1.30",
pages = "249--249",
abstract = "We propose a universal grapheme-phoneme transduction model using neuralized finite-state transducers. Many computational models of grapheme-phoneme transduction nowadays are based on the (autoregressive) sequence-to-sequence string transduction paradigm. While such models have achieved state-of-the-art performance, they suffer from theoretical limitations of autoregressive models. On the other hand, neuralized finite-state transducers (NFSTs) have shown promising results on various string transduction tasks. NFSTs can be seen as a generalization of weighted finite-state transducers (WFSTs), and can be seen as pairs of a featurized finite-state machine ({`}marked finite-state transducer{'} or MFST in NFST terminology), and a string scoring function. Instead of taking a product of local contextual feature weights on FST arcs, NFSTs can employ arbitrary scoring functions to weight global contextual features of a string transduction, and therefore break the Markov property. Furthermore, NFSTs can be formally shown to be more expressive than (autoregressive) seq2seq models. Empirically, joint grapheme-phoneme transduction NFSTs have consistently outperformed vanilla seq2seq models on grapheme-tophoneme and phoneme-to-grapheme transduction tasks for English. Furthermore, they provide interpretable aligned string transductions, thanks to their finite-state machine component. In this talk, we propose a multilingual extension of the joint grapheme-phoneme NFST. We achieve this goal by modeling typological and phylogenetic features of languages and scripts as optional latent variables using a finite-state machine. The result is a versatile graphemephoneme transduction model: in addition to standard monolingual and multilingual transduction, the proposed multilingual NFST can also be used in various controlled generation scenarios, such as phoneme-to-grapheme transduction of an unseen language-script pair. We also plan to release an NFST software package.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-2023-future">
<titleInfo>
<title>A future for universal grapheme-phoneme transduction modeling with neuralized finite-state transducers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chu-Cheng</namePart>
<namePart type="given">Lin</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th 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">Eleanor</namePart>
<namePart type="family">Chodroff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Mailhot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a universal grapheme-phoneme transduction model using neuralized finite-state transducers. Many computational models of grapheme-phoneme transduction nowadays are based on the (autoregressive) sequence-to-sequence string transduction paradigm. While such models have achieved state-of-the-art performance, they suffer from theoretical limitations of autoregressive models. On the other hand, neuralized finite-state transducers (NFSTs) have shown promising results on various string transduction tasks. NFSTs can be seen as a generalization of weighted finite-state transducers (WFSTs), and can be seen as pairs of a featurized finite-state machine (‘marked finite-state transducer’ or MFST in NFST terminology), and a string scoring function. Instead of taking a product of local contextual feature weights on FST arcs, NFSTs can employ arbitrary scoring functions to weight global contextual features of a string transduction, and therefore break the Markov property. Furthermore, NFSTs can be formally shown to be more expressive than (autoregressive) seq2seq models. Empirically, joint grapheme-phoneme transduction NFSTs have consistently outperformed vanilla seq2seq models on grapheme-tophoneme and phoneme-to-grapheme transduction tasks for English. Furthermore, they provide interpretable aligned string transductions, thanks to their finite-state machine component. In this talk, we propose a multilingual extension of the joint grapheme-phoneme NFST. We achieve this goal by modeling typological and phylogenetic features of languages and scripts as optional latent variables using a finite-state machine. The result is a versatile graphemephoneme transduction model: in addition to standard monolingual and multilingual transduction, the proposed multilingual NFST can also be used in various controlled generation scenarios, such as phoneme-to-grapheme transduction of an unseen language-script pair. We also plan to release an NFST software package.</abstract>
<identifier type="citekey">lin-2023-future</identifier>
<identifier type="doi">10.18653/v1/2023.sigmorphon-1.30</identifier>
<location>
<url>https://aclanthology.org/2023.sigmorphon-1.30</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>249</start>
<end>249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A future for universal grapheme-phoneme transduction modeling with neuralized finite-state transducers
%A Lin, Chu-Cheng Lin
%Y Nicolai, Garrett
%Y Chodroff, Eleanor
%Y Mailhot, Frederic
%Y Çöltekin, Çağrı
%S Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F lin-2023-future
%X We propose a universal grapheme-phoneme transduction model using neuralized finite-state transducers. Many computational models of grapheme-phoneme transduction nowadays are based on the (autoregressive) sequence-to-sequence string transduction paradigm. While such models have achieved state-of-the-art performance, they suffer from theoretical limitations of autoregressive models. On the other hand, neuralized finite-state transducers (NFSTs) have shown promising results on various string transduction tasks. NFSTs can be seen as a generalization of weighted finite-state transducers (WFSTs), and can be seen as pairs of a featurized finite-state machine (‘marked finite-state transducer’ or MFST in NFST terminology), and a string scoring function. Instead of taking a product of local contextual feature weights on FST arcs, NFSTs can employ arbitrary scoring functions to weight global contextual features of a string transduction, and therefore break the Markov property. Furthermore, NFSTs can be formally shown to be more expressive than (autoregressive) seq2seq models. Empirically, joint grapheme-phoneme transduction NFSTs have consistently outperformed vanilla seq2seq models on grapheme-tophoneme and phoneme-to-grapheme transduction tasks for English. Furthermore, they provide interpretable aligned string transductions, thanks to their finite-state machine component. In this talk, we propose a multilingual extension of the joint grapheme-phoneme NFST. We achieve this goal by modeling typological and phylogenetic features of languages and scripts as optional latent variables using a finite-state machine. The result is a versatile graphemephoneme transduction model: in addition to standard monolingual and multilingual transduction, the proposed multilingual NFST can also be used in various controlled generation scenarios, such as phoneme-to-grapheme transduction of an unseen language-script pair. We also plan to release an NFST software package.
%R 10.18653/v1/2023.sigmorphon-1.30
%U https://aclanthology.org/2023.sigmorphon-1.30
%U https://doi.org/10.18653/v1/2023.sigmorphon-1.30
%P 249-249
Markdown (Informal)
[A future for universal grapheme-phoneme transduction modeling with neuralized finite-state transducers](https://aclanthology.org/2023.sigmorphon-1.30) (Lin, SIGMORPHON 2023)
ACL