@inproceedings{silfverberg-etal-2021-rnn,
title = "Do {RNN} States Encode Abstract Phonological Alternations?",
author = "Silfverberg, Miikka and
Tyers, Francis and
Nicolai, Garrett and
Hulden, Mans",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.435/",
doi = "10.18653/v1/2021.naacl-main.435",
pages = "5501--5513",
abstract = "Sequence-to-sequence models have delivered impressive results in word formation tasks such as morphological inflection, often learning to model subtle morphophonological details with limited training data. Despite the performance, the opacity of neural models makes it difficult to determine whether complex generalizations are learned, or whether a kind of separate rote memorization of each morphophonological process takes place. To investigate whether complex alternations are simply memorized or whether there is some level of generalization across related sound changes in a sequence-to-sequence model, we perform several experiments on Finnish consonant gradation{---}a complex set of sound changes triggered in some words by certain suffixes. We find that our models often{---}though not always{---}encode 17 different consonant gradation processes in a handful of dimensions in the RNN. We also show that by scaling the activations in these dimensions we can control whether consonant gradation occurs and the direction of the gradation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="silfverberg-etal-2021-rnn">
<titleInfo>
<title>Do RNN States Encode Abstract Phonological Alternations?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miikka</namePart>
<namePart type="family">Silfverberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mans</namePart>
<namePart type="family">Hulden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</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>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Sequence-to-sequence models have delivered impressive results in word formation tasks such as morphological inflection, often learning to model subtle morphophonological details with limited training data. Despite the performance, the opacity of neural models makes it difficult to determine whether complex generalizations are learned, or whether a kind of separate rote memorization of each morphophonological process takes place. To investigate whether complex alternations are simply memorized or whether there is some level of generalization across related sound changes in a sequence-to-sequence model, we perform several experiments on Finnish consonant gradation—a complex set of sound changes triggered in some words by certain suffixes. We find that our models often—though not always—encode 17 different consonant gradation processes in a handful of dimensions in the RNN. We also show that by scaling the activations in these dimensions we can control whether consonant gradation occurs and the direction of the gradation.</abstract>
<identifier type="citekey">silfverberg-etal-2021-rnn</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.435</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.435/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5501</start>
<end>5513</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do RNN States Encode Abstract Phonological Alternations?
%A Silfverberg, Miikka
%A Tyers, Francis
%A Nicolai, Garrett
%A Hulden, Mans
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F silfverberg-etal-2021-rnn
%X Sequence-to-sequence models have delivered impressive results in word formation tasks such as morphological inflection, often learning to model subtle morphophonological details with limited training data. Despite the performance, the opacity of neural models makes it difficult to determine whether complex generalizations are learned, or whether a kind of separate rote memorization of each morphophonological process takes place. To investigate whether complex alternations are simply memorized or whether there is some level of generalization across related sound changes in a sequence-to-sequence model, we perform several experiments on Finnish consonant gradation—a complex set of sound changes triggered in some words by certain suffixes. We find that our models often—though not always—encode 17 different consonant gradation processes in a handful of dimensions in the RNN. We also show that by scaling the activations in these dimensions we can control whether consonant gradation occurs and the direction of the gradation.
%R 10.18653/v1/2021.naacl-main.435
%U https://aclanthology.org/2021.naacl-main.435/
%U https://doi.org/10.18653/v1/2021.naacl-main.435
%P 5501-5513
Markdown (Informal)
[Do RNN States Encode Abstract Phonological Alternations?](https://aclanthology.org/2021.naacl-main.435/) (Silfverberg et al., NAACL 2021)
ACL
- Miikka Silfverberg, Francis Tyers, Garrett Nicolai, and Mans Hulden. 2021. Do RNN States Encode Abstract Phonological Alternations?. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5501–5513, Online. Association for Computational Linguistics.