@inproceedings{forster-etal-2021-searching,
title = "Searching for Search Errors in Neural Morphological Inflection",
author = "Forster, Martina and
Meister, Clara and
Cotterell, Ryan",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.118",
doi = "10.18653/v1/2021.eacl-main.118",
pages = "1388--1394",
abstract = "Neural sequence-to-sequence models are currently the predominant choice for language generation tasks. Yet, on word-level tasks, exact inference of these models reveals the empty string is often the global optimum. Prior works have speculated this phenomenon is a result of the inadequacy of neural models for language generation. However, in the case of morphological inflection, we find that the empty string is almost never the most probable solution under the model. Further, greedy search often finds the global optimum. These observations suggest that the poor calibration of many neural models may stem from characteristics of a specific subset of tasks rather than general ill-suitedness of such models for language generation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="forster-etal-2021-searching">
<titleInfo>
<title>Searching for Search Errors in Neural Morphological Inflection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martina</namePart>
<namePart type="family">Forster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clara</namePart>
<namePart type="family">Meister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</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>Neural sequence-to-sequence models are currently the predominant choice for language generation tasks. Yet, on word-level tasks, exact inference of these models reveals the empty string is often the global optimum. Prior works have speculated this phenomenon is a result of the inadequacy of neural models for language generation. However, in the case of morphological inflection, we find that the empty string is almost never the most probable solution under the model. Further, greedy search often finds the global optimum. These observations suggest that the poor calibration of many neural models may stem from characteristics of a specific subset of tasks rather than general ill-suitedness of such models for language generation.</abstract>
<identifier type="citekey">forster-etal-2021-searching</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.118</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.118</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1388</start>
<end>1394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Searching for Search Errors in Neural Morphological Inflection
%A Forster, Martina
%A Meister, Clara
%A Cotterell, Ryan
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F forster-etal-2021-searching
%X Neural sequence-to-sequence models are currently the predominant choice for language generation tasks. Yet, on word-level tasks, exact inference of these models reveals the empty string is often the global optimum. Prior works have speculated this phenomenon is a result of the inadequacy of neural models for language generation. However, in the case of morphological inflection, we find that the empty string is almost never the most probable solution under the model. Further, greedy search often finds the global optimum. These observations suggest that the poor calibration of many neural models may stem from characteristics of a specific subset of tasks rather than general ill-suitedness of such models for language generation.
%R 10.18653/v1/2021.eacl-main.118
%U https://aclanthology.org/2021.eacl-main.118
%U https://doi.org/10.18653/v1/2021.eacl-main.118
%P 1388-1394
Markdown (Informal)
[Searching for Search Errors in Neural Morphological Inflection](https://aclanthology.org/2021.eacl-main.118) (Forster et al., EACL 2021)
ACL
- Martina Forster, Clara Meister, and Ryan Cotterell. 2021. Searching for Search Errors in Neural Morphological Inflection. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1388–1394, Online. Association for Computational Linguistics.