@inproceedings{kim-etal-2024-rt-vq2a2,
title = "{RT}-{VQ}2{A}2: Real Time Vector Quantized Question Answering with {ASR}",
author = "Kim, Kyungho and
Park, Seongmin and
Lee, Jihwa",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1238",
pages = "14204--14214",
abstract = "In Spoken Question Answering (SQA), automatic speech recognition (ASR) outputs are often relayed to language models for QA. However, constructing such a cascaded framework with large language models (LLMs) in a real-time SQA setting involves realistic challenges, such as noise in the ASR output, the limited context length of LLMs, and latency in processing large models. This paper proposes a novel model-agnostic framework, RT-VQ2A2, to address these challenges. RT-VQ2A2 consists of three steps: codebook preparation, quantized semantic vector extractor, and dual segment selector. We construct a codebook from clustering, removing outliers on a text corpus derived from ASR to mitigate the influence of ASR error. Extracting quantized semantic vectors through a pre-built codebook shows significant speed and performance improvements in relevant context retrieval. Dual segment selector considers both semantic and lexical aspects to deal with ASR error. The efficacy of RT-VQ2A2 is validated on the widely used Spoken-SQuAD dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2024-rt-vq2a2">
<titleInfo>
<title>RT-VQ2A2: Real Time Vector Quantized Question Answering with ASR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyungho</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seongmin</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihwa</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In Spoken Question Answering (SQA), automatic speech recognition (ASR) outputs are often relayed to language models for QA. However, constructing such a cascaded framework with large language models (LLMs) in a real-time SQA setting involves realistic challenges, such as noise in the ASR output, the limited context length of LLMs, and latency in processing large models. This paper proposes a novel model-agnostic framework, RT-VQ2A2, to address these challenges. RT-VQ2A2 consists of three steps: codebook preparation, quantized semantic vector extractor, and dual segment selector. We construct a codebook from clustering, removing outliers on a text corpus derived from ASR to mitigate the influence of ASR error. Extracting quantized semantic vectors through a pre-built codebook shows significant speed and performance improvements in relevant context retrieval. Dual segment selector considers both semantic and lexical aspects to deal with ASR error. The efficacy of RT-VQ2A2 is validated on the widely used Spoken-SQuAD dataset.</abstract>
<identifier type="citekey">kim-etal-2024-rt-vq2a2</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1238</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14204</start>
<end>14214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RT-VQ2A2: Real Time Vector Quantized Question Answering with ASR
%A Kim, Kyungho
%A Park, Seongmin
%A Lee, Jihwa
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kim-etal-2024-rt-vq2a2
%X In Spoken Question Answering (SQA), automatic speech recognition (ASR) outputs are often relayed to language models for QA. However, constructing such a cascaded framework with large language models (LLMs) in a real-time SQA setting involves realistic challenges, such as noise in the ASR output, the limited context length of LLMs, and latency in processing large models. This paper proposes a novel model-agnostic framework, RT-VQ2A2, to address these challenges. RT-VQ2A2 consists of three steps: codebook preparation, quantized semantic vector extractor, and dual segment selector. We construct a codebook from clustering, removing outliers on a text corpus derived from ASR to mitigate the influence of ASR error. Extracting quantized semantic vectors through a pre-built codebook shows significant speed and performance improvements in relevant context retrieval. Dual segment selector considers both semantic and lexical aspects to deal with ASR error. The efficacy of RT-VQ2A2 is validated on the widely used Spoken-SQuAD dataset.
%U https://aclanthology.org/2024.lrec-main.1238
%P 14204-14214
Markdown (Informal)
[RT-VQ2A2: Real Time Vector Quantized Question Answering with ASR](https://aclanthology.org/2024.lrec-main.1238) (Kim et al., LREC-COLING 2024)
ACL