@inproceedings{golany-etal-2024-efficient,
title = "Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts",
author = "Golany, Lotem and
Galgani, Filippo and
Mamo, Maya and
Parasol, Nimrod and
Vandsburger, Omer and
Bar, Nadav and
Dagan, Ido",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.106/",
doi = "10.18653/v1/2024.findings-emnlp.106",
pages = "1908--1925",
abstract = "Automating data generation with Large Language Models (LLMs) has become increasingly popular. In this work, we investigate the feasibility and effectiveness of LLM-based data generation in the challenging setting of source-grounded information-seeking dialogs, with response attribution, over long documents. Our source texts consist of long and noisy meeting transcripts, adding to the task complexity. Since automating attribution remains difficult, we propose a semi-automatic approach: dialog queries and responses are generated with LLMs, followed by human verification and identification of attribution spans. Using this approach, we created MISeD {--} Meeting Information Seeking Dialogs dataset {--} a dataset of information-seeking dialogs focused on meeting transcripts. Models finetuned with MISeD demonstrate superior performance compared to off-the-shelf models, even those of larger size. Finetuning on MISeD gives comparable response generation quality to finetuning on fully manual data, while improving attribution quality and reducing time and effort."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="golany-etal-2024-efficient">
<titleInfo>
<title>Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lotem</namePart>
<namePart type="family">Golany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filippo</namePart>
<namePart type="family">Galgani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maya</namePart>
<namePart type="family">Mamo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nimrod</namePart>
<namePart type="family">Parasol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Vandsburger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadav</namePart>
<namePart type="family">Bar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Dagan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automating data generation with Large Language Models (LLMs) has become increasingly popular. In this work, we investigate the feasibility and effectiveness of LLM-based data generation in the challenging setting of source-grounded information-seeking dialogs, with response attribution, over long documents. Our source texts consist of long and noisy meeting transcripts, adding to the task complexity. Since automating attribution remains difficult, we propose a semi-automatic approach: dialog queries and responses are generated with LLMs, followed by human verification and identification of attribution spans. Using this approach, we created MISeD – Meeting Information Seeking Dialogs dataset – a dataset of information-seeking dialogs focused on meeting transcripts. Models finetuned with MISeD demonstrate superior performance compared to off-the-shelf models, even those of larger size. Finetuning on MISeD gives comparable response generation quality to finetuning on fully manual data, while improving attribution quality and reducing time and effort.</abstract>
<identifier type="citekey">golany-etal-2024-efficient</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.106</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.106/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1908</start>
<end>1925</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts
%A Golany, Lotem
%A Galgani, Filippo
%A Mamo, Maya
%A Parasol, Nimrod
%A Vandsburger, Omer
%A Bar, Nadav
%A Dagan, Ido
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F golany-etal-2024-efficient
%X Automating data generation with Large Language Models (LLMs) has become increasingly popular. In this work, we investigate the feasibility and effectiveness of LLM-based data generation in the challenging setting of source-grounded information-seeking dialogs, with response attribution, over long documents. Our source texts consist of long and noisy meeting transcripts, adding to the task complexity. Since automating attribution remains difficult, we propose a semi-automatic approach: dialog queries and responses are generated with LLMs, followed by human verification and identification of attribution spans. Using this approach, we created MISeD – Meeting Information Seeking Dialogs dataset – a dataset of information-seeking dialogs focused on meeting transcripts. Models finetuned with MISeD demonstrate superior performance compared to off-the-shelf models, even those of larger size. Finetuning on MISeD gives comparable response generation quality to finetuning on fully manual data, while improving attribution quality and reducing time and effort.
%R 10.18653/v1/2024.findings-emnlp.106
%U https://aclanthology.org/2024.findings-emnlp.106/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.106
%P 1908-1925
Markdown (Informal)
[Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts](https://aclanthology.org/2024.findings-emnlp.106/) (Golany et al., Findings 2024)
ACL
- Lotem Golany, Filippo Galgani, Maya Mamo, Nimrod Parasol, Omer Vandsburger, Nadav Bar, and Ido Dagan. 2024. Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 1908–1925, Miami, Florida, USA. Association for Computational Linguistics.