@inproceedings{lewis-etal-2024-insights,
title = "Insights of a Usability Study for {KBQA} Interactive Semantic Parsing: Generation Yields Benefits over Templates but External Validity Remains Challenging",
author = "Lewis, Ashley and
Mo, Lingbo and
de Marneffe, Marie-Catherine and
Sun, Huan and
White, Michael",
editor = "Balloccu, Simone and
Belz, Anya and
Huidrom, Rudali and
Reiter, Ehud and
Sedoc, Joao and
Thomson, Craig",
booktitle = "Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.humeval-1.5",
pages = "47--62",
abstract = "We present our findings from a usability study of an interactive semantic parsing system for knowledge based question answering (KBQA). The system is designed to help users access information within a knowledge base without having to know its query language. The system translates the user{'}s question into the query language, retrieves an answer, then presents an English explanation of the process so that the user can make corrections if necessary. To our knowledge, our work is the most thorough usability study conducted for such a system and the only one that uses crowdworkers as participants to verify that the system is usable for average users. Our crowdworkers participate in KBQA dialogues using 4 versions of a system based on the framework by Mo et al. (2022) and answer surveys about their experiences. Some key takeaways from this work are: 1) we provide evidence for the benefits of interactivity in semantic parsing with human users and using generated questions in lieu of templated representations, 2) we identify limitations of simulations and provide contrasting evidence from actual system use, and 3) we provide an examination of crowdsourcing methodology, in particular the trade-offs of using crowdworkers vs. a specially trained group of evaluators.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lewis-etal-2024-insights">
<titleInfo>
<title>Insights of a Usability Study for KBQA Interactive Semantic Parsing: Generation Yields Benefits over Templates but External Validity Remains Challenging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashley</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingbo</namePart>
<namePart type="family">Mo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">White</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 Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Balloccu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudali</namePart>
<namePart type="family">Huidrom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joao</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Thomson</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>We present our findings from a usability study of an interactive semantic parsing system for knowledge based question answering (KBQA). The system is designed to help users access information within a knowledge base without having to know its query language. The system translates the user’s question into the query language, retrieves an answer, then presents an English explanation of the process so that the user can make corrections if necessary. To our knowledge, our work is the most thorough usability study conducted for such a system and the only one that uses crowdworkers as participants to verify that the system is usable for average users. Our crowdworkers participate in KBQA dialogues using 4 versions of a system based on the framework by Mo et al. (2022) and answer surveys about their experiences. Some key takeaways from this work are: 1) we provide evidence for the benefits of interactivity in semantic parsing with human users and using generated questions in lieu of templated representations, 2) we identify limitations of simulations and provide contrasting evidence from actual system use, and 3) we provide an examination of crowdsourcing methodology, in particular the trade-offs of using crowdworkers vs. a specially trained group of evaluators.</abstract>
<identifier type="citekey">lewis-etal-2024-insights</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.5</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>47</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Insights of a Usability Study for KBQA Interactive Semantic Parsing: Generation Yields Benefits over Templates but External Validity Remains Challenging
%A Lewis, Ashley
%A Mo, Lingbo
%A de Marneffe, Marie-Catherine
%A Sun, Huan
%A White, Michael
%Y Balloccu, Simone
%Y Belz, Anya
%Y Huidrom, Rudali
%Y Reiter, Ehud
%Y Sedoc, Joao
%Y Thomson, Craig
%S Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lewis-etal-2024-insights
%X We present our findings from a usability study of an interactive semantic parsing system for knowledge based question answering (KBQA). The system is designed to help users access information within a knowledge base without having to know its query language. The system translates the user’s question into the query language, retrieves an answer, then presents an English explanation of the process so that the user can make corrections if necessary. To our knowledge, our work is the most thorough usability study conducted for such a system and the only one that uses crowdworkers as participants to verify that the system is usable for average users. Our crowdworkers participate in KBQA dialogues using 4 versions of a system based on the framework by Mo et al. (2022) and answer surveys about their experiences. Some key takeaways from this work are: 1) we provide evidence for the benefits of interactivity in semantic parsing with human users and using generated questions in lieu of templated representations, 2) we identify limitations of simulations and provide contrasting evidence from actual system use, and 3) we provide an examination of crowdsourcing methodology, in particular the trade-offs of using crowdworkers vs. a specially trained group of evaluators.
%U https://aclanthology.org/2024.humeval-1.5
%P 47-62
Markdown (Informal)
[Insights of a Usability Study for KBQA Interactive Semantic Parsing: Generation Yields Benefits over Templates but External Validity Remains Challenging](https://aclanthology.org/2024.humeval-1.5) (Lewis et al., HumEval-WS 2024)
ACL