@inproceedings{rohanian-etal-2023-disfluent,
title = "Disfluent Cues for Enhanced Speech Understanding in Large Language Models",
author = "Rohanian, Morteza and
Nooralahzadeh, Farhad and
Rohanian, Omid and
Clifton, David and
Krauthammer, Michael",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.238",
doi = "10.18653/v1/2023.findings-emnlp.238",
pages = "3676--3684",
abstract = "In computational linguistics, the common practice is to {``}clean{''} disfluent content from spontaneous speech. However, we hypothesize that these disfluencies might serve as more than mere noise, potentially acting as informative cues. We use a range of pre-trained models for a reading comprehension task involving disfluent queries, specifically featuring different types of speech repairs. The findings indicate that certain disfluencies can indeed improve model performance, particularly those stemming from context-based adjustments. However, large-scale language models struggle to handle repairs involving decision-making or the correction of lexical or syntactic errors, suggesting a crucial area for potential improvement. This paper thus highlights the importance of a nuanced approach to disfluencies, advocating for their potential utility in enhancing model performance rather than their removal.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rohanian-etal-2023-disfluent">
<titleInfo>
<title>Disfluent Cues for Enhanced Speech Understanding in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Morteza</namePart>
<namePart type="family">Rohanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farhad</namePart>
<namePart type="family">Nooralahzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omid</namePart>
<namePart type="family">Rohanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Clifton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Krauthammer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In computational linguistics, the common practice is to “clean” disfluent content from spontaneous speech. However, we hypothesize that these disfluencies might serve as more than mere noise, potentially acting as informative cues. We use a range of pre-trained models for a reading comprehension task involving disfluent queries, specifically featuring different types of speech repairs. The findings indicate that certain disfluencies can indeed improve model performance, particularly those stemming from context-based adjustments. However, large-scale language models struggle to handle repairs involving decision-making or the correction of lexical or syntactic errors, suggesting a crucial area for potential improvement. This paper thus highlights the importance of a nuanced approach to disfluencies, advocating for their potential utility in enhancing model performance rather than their removal.</abstract>
<identifier type="citekey">rohanian-etal-2023-disfluent</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.238</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.238</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>3676</start>
<end>3684</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disfluent Cues for Enhanced Speech Understanding in Large Language Models
%A Rohanian, Morteza
%A Nooralahzadeh, Farhad
%A Rohanian, Omid
%A Clifton, David
%A Krauthammer, Michael
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F rohanian-etal-2023-disfluent
%X In computational linguistics, the common practice is to “clean” disfluent content from spontaneous speech. However, we hypothesize that these disfluencies might serve as more than mere noise, potentially acting as informative cues. We use a range of pre-trained models for a reading comprehension task involving disfluent queries, specifically featuring different types of speech repairs. The findings indicate that certain disfluencies can indeed improve model performance, particularly those stemming from context-based adjustments. However, large-scale language models struggle to handle repairs involving decision-making or the correction of lexical or syntactic errors, suggesting a crucial area for potential improvement. This paper thus highlights the importance of a nuanced approach to disfluencies, advocating for their potential utility in enhancing model performance rather than their removal.
%R 10.18653/v1/2023.findings-emnlp.238
%U https://aclanthology.org/2023.findings-emnlp.238
%U https://doi.org/10.18653/v1/2023.findings-emnlp.238
%P 3676-3684
Markdown (Informal)
[Disfluent Cues for Enhanced Speech Understanding in Large Language Models](https://aclanthology.org/2023.findings-emnlp.238) (Rohanian et al., Findings 2023)
ACL