@inproceedings{wan-etal-2020-subtitles,
title = "Subtitles to Segmentation: Improving Low-Resource Speech-to-{T}ext{T}ranslation Pipelines",
author = "Wan, David and
Jiang, Zhengping and
Kedzie, Chris and
Turcan, Elsbeth and
Bell, Peter and
McKeown, Kathy",
editor = "McKeown, Kathy and
Oard, Douglas W. and
{Elizabeth} and
Schwartz, Richard",
booktitle = "Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.clssts-1.11",
pages = "68--73",
abstract = "In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation. ASR output segmentation is crucial, as ASR systems segment the input audio using purely acoustic information and are not guaranteed to output sentence-like segments. Since most MT systems expect sentences as input, feeding in longer unsegmented passages can lead to sub-optimal performance. We explore the feasibility of using datasets of subtitles from TV shows and movies to train better ASR segmentation models. We further incorporate part-of-speech (POS) tag and dependency label information (derived from the unsegmented ASR outputs) into our segmentation model. We show that this noisy syntactic information can improve model accuracy. We evaluate our models intrinsically on segmentation quality and extrinsically on downstream MT performance, as well as downstream tasks including cross-lingual information retrieval (CLIR) tasks and human relevance assessments. Our model shows improved performance on downstream tasks for Lithuanian and Bulgarian.",
language = "English",
ISBN = "979-10-95546-55-9",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wan-etal-2020-subtitles">
<titleInfo>
<title>Subtitles to Segmentation: Improving Low-Resource Speech-to-TextTranslation Pipelines</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengping</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Kedzie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elsbeth</namePart>
<namePart type="family">Turcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Bell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathy</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kathy</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Oard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name>
<namePart>Elizabeth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-55-9</identifier>
</relatedItem>
<abstract>In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation. ASR output segmentation is crucial, as ASR systems segment the input audio using purely acoustic information and are not guaranteed to output sentence-like segments. Since most MT systems expect sentences as input, feeding in longer unsegmented passages can lead to sub-optimal performance. We explore the feasibility of using datasets of subtitles from TV shows and movies to train better ASR segmentation models. We further incorporate part-of-speech (POS) tag and dependency label information (derived from the unsegmented ASR outputs) into our segmentation model. We show that this noisy syntactic information can improve model accuracy. We evaluate our models intrinsically on segmentation quality and extrinsically on downstream MT performance, as well as downstream tasks including cross-lingual information retrieval (CLIR) tasks and human relevance assessments. Our model shows improved performance on downstream tasks for Lithuanian and Bulgarian.</abstract>
<identifier type="citekey">wan-etal-2020-subtitles</identifier>
<location>
<url>https://aclanthology.org/2020.clssts-1.11</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>68</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Subtitles to Segmentation: Improving Low-Resource Speech-to-TextTranslation Pipelines
%A Wan, David
%A Jiang, Zhengping
%A Kedzie, Chris
%A Turcan, Elsbeth
%A Bell, Peter
%A McKeown, Kathy
%Y McKeown, Kathy
%Y Oard, Douglas W.
%Y Schwartz, Richard
%E Elizabeth
%S Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020)
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-55-9
%G English
%F wan-etal-2020-subtitles
%X In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation. ASR output segmentation is crucial, as ASR systems segment the input audio using purely acoustic information and are not guaranteed to output sentence-like segments. Since most MT systems expect sentences as input, feeding in longer unsegmented passages can lead to sub-optimal performance. We explore the feasibility of using datasets of subtitles from TV shows and movies to train better ASR segmentation models. We further incorporate part-of-speech (POS) tag and dependency label information (derived from the unsegmented ASR outputs) into our segmentation model. We show that this noisy syntactic information can improve model accuracy. We evaluate our models intrinsically on segmentation quality and extrinsically on downstream MT performance, as well as downstream tasks including cross-lingual information retrieval (CLIR) tasks and human relevance assessments. Our model shows improved performance on downstream tasks for Lithuanian and Bulgarian.
%U https://aclanthology.org/2020.clssts-1.11
%P 68-73
Markdown (Informal)
[Subtitles to Segmentation: Improving Low-Resource Speech-to-TextTranslation Pipelines](https://aclanthology.org/2020.clssts-1.11) (Wan et al., CLSSTS 2020)
ACL