@inproceedings{sanabria-etal-2021-difficulty,
title = "On the Difficulty of Segmenting Words with Attention",
author = "Sanabria, Ramon and
Tang, Hao and
Goldwater, Sharon",
editor = "Sedoc, Jo{\~a}o and
Rogers, Anna and
Rumshisky, Anna and
Tafreshi, Shabnam",
booktitle = "Proceedings of the Second Workshop on Insights from Negative Results in NLP",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.insights-1.11",
doi = "10.18653/v1/2021.insights-1.11",
pages = "67--73",
abstract = "Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition, attention can be used to locate and segment the words. We show, however, that even on monolingual data this approach is brittle. In our experiments with different input types, data sizes, and segmentation algorithms, only models trained to predict phones from words succeed in the task. Models trained to predict words from either phones or speech (i.e., the opposite direction needed to generalize to new data), yield much worse results, suggesting that attention-based segmentation is only useful in limited scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanabria-etal-2021-difficulty">
<titleInfo>
<title>On the Difficulty of Segmenting Words with Attention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramon</namePart>
<namePart type="family">Sanabria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharon</namePart>
<namePart type="family">Goldwater</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</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">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition, attention can be used to locate and segment the words. We show, however, that even on monolingual data this approach is brittle. In our experiments with different input types, data sizes, and segmentation algorithms, only models trained to predict phones from words succeed in the task. Models trained to predict words from either phones or speech (i.e., the opposite direction needed to generalize to new data), yield much worse results, suggesting that attention-based segmentation is only useful in limited scenarios.</abstract>
<identifier type="citekey">sanabria-etal-2021-difficulty</identifier>
<identifier type="doi">10.18653/v1/2021.insights-1.11</identifier>
<location>
<url>https://aclanthology.org/2021.insights-1.11</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>67</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Difficulty of Segmenting Words with Attention
%A Sanabria, Ramon
%A Tang, Hao
%A Goldwater, Sharon
%Y Sedoc, João
%Y Rogers, Anna
%Y Rumshisky, Anna
%Y Tafreshi, Shabnam
%S Proceedings of the Second Workshop on Insights from Negative Results in NLP
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F sanabria-etal-2021-difficulty
%X Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition, attention can be used to locate and segment the words. We show, however, that even on monolingual data this approach is brittle. In our experiments with different input types, data sizes, and segmentation algorithms, only models trained to predict phones from words succeed in the task. Models trained to predict words from either phones or speech (i.e., the opposite direction needed to generalize to new data), yield much worse results, suggesting that attention-based segmentation is only useful in limited scenarios.
%R 10.18653/v1/2021.insights-1.11
%U https://aclanthology.org/2021.insights-1.11
%U https://doi.org/10.18653/v1/2021.insights-1.11
%P 67-73
Markdown (Informal)
[On the Difficulty of Segmenting Words with Attention](https://aclanthology.org/2021.insights-1.11) (Sanabria et al., insights 2021)
ACL
- Ramon Sanabria, Hao Tang, and Sharon Goldwater. 2021. On the Difficulty of Segmenting Words with Attention. In Proceedings of the Second Workshop on Insights from Negative Results in NLP, pages 67–73, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.