@inproceedings{ramanan-2023-corpus,
title = "Corpus-Based Task-Specific Relation Discovery",
author = "Ramanan, Karthik",
editor = "Hruschka, Estevam and
Mitchell, Tom and
Rahman, Sajjadur and
Mladeni{\'c}, Dunja and
Grobelnik, Marko",
booktitle = "Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023)",
month = jul,
year = "2023",
address = "Toronto, ON, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.matching-1.5/",
doi = "10.18653/v1/2023.matching-1.5",
pages = "45--57",
abstract = "Relation extraction is a crucial language processing task for various downstream applications, including knowledge base completion, question answering, and summarization. Traditional relation-extraction techniques, however, rely on a predefined set of relations and model the extraction as a classification task. Consequently, such closed-world extraction methods are insufficient for inducing novel relations from a corpus. Unsupervised techniques like OpenIE, which extract {\ensuremath{<}}head, relation, tail{\ensuremath{>}} triples, generate relations that are too general for practical information extraction applications. In this work, we contribute the following: 1) We motivate and introduce a new task, corpus-based task-specific relation discovery. 2) We adapt existing data sources to create Wiki-Art, a novel dataset for task-specific relation discovery. 3) We develop a novel framework for relation discovery using zero-shot entity linking, prompting, and type-specific clustering. Our approach effectively connects unstructured text spans to their shared underlying relations, bridging the data-representation gap and significantly outperforming baselines on both quantitative and qualitative metrics. Our code and data are available in our GitHub repository."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramanan-2023-corpus">
<titleInfo>
<title>Corpus-Based Task-Specific Relation Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Ramanan</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>Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Estevam</namePart>
<namePart type="family">Hruschka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Mitchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajjadur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dunja</namePart>
<namePart type="family">Mladenić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, ON, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Relation extraction is a crucial language processing task for various downstream applications, including knowledge base completion, question answering, and summarization. Traditional relation-extraction techniques, however, rely on a predefined set of relations and model the extraction as a classification task. Consequently, such closed-world extraction methods are insufficient for inducing novel relations from a corpus. Unsupervised techniques like OpenIE, which extract \ensuremath<head, relation, tail\ensuremath> triples, generate relations that are too general for practical information extraction applications. In this work, we contribute the following: 1) We motivate and introduce a new task, corpus-based task-specific relation discovery. 2) We adapt existing data sources to create Wiki-Art, a novel dataset for task-specific relation discovery. 3) We develop a novel framework for relation discovery using zero-shot entity linking, prompting, and type-specific clustering. Our approach effectively connects unstructured text spans to their shared underlying relations, bridging the data-representation gap and significantly outperforming baselines on both quantitative and qualitative metrics. Our code and data are available in our GitHub repository.</abstract>
<identifier type="citekey">ramanan-2023-corpus</identifier>
<identifier type="doi">10.18653/v1/2023.matching-1.5</identifier>
<location>
<url>https://aclanthology.org/2023.matching-1.5/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>45</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus-Based Task-Specific Relation Discovery
%A Ramanan, Karthik
%Y Hruschka, Estevam
%Y Mitchell, Tom
%Y Rahman, Sajjadur
%Y Mladenić, Dunja
%Y Grobelnik, Marko
%S Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, ON, Canada
%F ramanan-2023-corpus
%X Relation extraction is a crucial language processing task for various downstream applications, including knowledge base completion, question answering, and summarization. Traditional relation-extraction techniques, however, rely on a predefined set of relations and model the extraction as a classification task. Consequently, such closed-world extraction methods are insufficient for inducing novel relations from a corpus. Unsupervised techniques like OpenIE, which extract \ensuremath<head, relation, tail\ensuremath> triples, generate relations that are too general for practical information extraction applications. In this work, we contribute the following: 1) We motivate and introduce a new task, corpus-based task-specific relation discovery. 2) We adapt existing data sources to create Wiki-Art, a novel dataset for task-specific relation discovery. 3) We develop a novel framework for relation discovery using zero-shot entity linking, prompting, and type-specific clustering. Our approach effectively connects unstructured text spans to their shared underlying relations, bridging the data-representation gap and significantly outperforming baselines on both quantitative and qualitative metrics. Our code and data are available in our GitHub repository.
%R 10.18653/v1/2023.matching-1.5
%U https://aclanthology.org/2023.matching-1.5/
%U https://doi.org/10.18653/v1/2023.matching-1.5
%P 45-57
Markdown (Informal)
[Corpus-Based Task-Specific Relation Discovery](https://aclanthology.org/2023.matching-1.5/) (Ramanan, MATCHING 2023)
ACL
- Karthik Ramanan. 2023. Corpus-Based Task-Specific Relation Discovery. In Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023), pages 45–57, Toronto, ON, Canada. Association for Computational Linguistics.