@inproceedings{banerjee-etal-2023-role,
title = "The Role of Output Vocabulary in {T}2{T} {LM}s for {SPARQL} Semantic Parsing",
author = "Banerjee, Debayan and
Nair, Pranav and
Usbeck, Ricardo and
Biemann, Chris",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.774",
doi = "10.18653/v1/2023.findings-acl.774",
pages = "12219--12228",
abstract = "In this work, we analyse the role of output vocabulary for text-to-text (T2T) models on the task of SPARQL semantic parsing. We perform experiments within the the context of knowledge graph question answering (KGQA), where the task is to convert questions in natural language to the SPARQL query language. We observe that the query vocabulary is distinct from human vocabulary. Language Models (LMs) are pre-dominantly trained for human language tasks, and hence, if the query vocabulary is replaced with a vocabulary more attuned to the LM tokenizer, the performance of models may improve. We carry out carefully selected vocabulary substitutions on the queries and find absolute gains in the range of 17{\%} on the GrailQA dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="banerjee-etal-2023-role">
<titleInfo>
<title>The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Debayan</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Nair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Usbeck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we analyse the role of output vocabulary for text-to-text (T2T) models on the task of SPARQL semantic parsing. We perform experiments within the the context of knowledge graph question answering (KGQA), where the task is to convert questions in natural language to the SPARQL query language. We observe that the query vocabulary is distinct from human vocabulary. Language Models (LMs) are pre-dominantly trained for human language tasks, and hence, if the query vocabulary is replaced with a vocabulary more attuned to the LM tokenizer, the performance of models may improve. We carry out carefully selected vocabulary substitutions on the queries and find absolute gains in the range of 17% on the GrailQA dataset.</abstract>
<identifier type="citekey">banerjee-etal-2023-role</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.774</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.774</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>12219</start>
<end>12228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing
%A Banerjee, Debayan
%A Nair, Pranav
%A Usbeck, Ricardo
%A Biemann, Chris
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F banerjee-etal-2023-role
%X In this work, we analyse the role of output vocabulary for text-to-text (T2T) models on the task of SPARQL semantic parsing. We perform experiments within the the context of knowledge graph question answering (KGQA), where the task is to convert questions in natural language to the SPARQL query language. We observe that the query vocabulary is distinct from human vocabulary. Language Models (LMs) are pre-dominantly trained for human language tasks, and hence, if the query vocabulary is replaced with a vocabulary more attuned to the LM tokenizer, the performance of models may improve. We carry out carefully selected vocabulary substitutions on the queries and find absolute gains in the range of 17% on the GrailQA dataset.
%R 10.18653/v1/2023.findings-acl.774
%U https://aclanthology.org/2023.findings-acl.774
%U https://doi.org/10.18653/v1/2023.findings-acl.774
%P 12219-12228
Markdown (Informal)
[The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing](https://aclanthology.org/2023.findings-acl.774) (Banerjee et al., Findings 2023)
ACL