@inproceedings{baek-etal-2023-direct,
title = "Direct Fact Retrieval from Knowledge Graphs without Entity Linking",
author = "Baek, Jinheon and
Aji, Alham Fikri and
Lehmann, Jens and
Hwang, Sung Ju",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.558",
doi = "10.18653/v1/2023.acl-long.558",
pages = "10038--10055",
abstract = "There has been a surge of interest in utilizing Knowledge Graphs (KGs) for various natural language processing/understanding tasks. The conventional mechanism to retrieve facts in KGs usually involves three steps: entity span detection, entity disambiguation, and relation classification. However, this approach requires additional labels for training each of the three subcomponents in addition to pairs of input texts and facts, and also may accumulate errors propagated from failures in previous steps. To tackle these limitations, we propose a simple knowledge retrieval framework, which directly retrieves facts from the KGs given the input text based on their representational similarities, which we refer to as Direct Fact Retrieval (DiFaR). Specifically, we first embed all facts in KGs onto a dense embedding space by using a language model trained by only pairs of input texts and facts, and then provide the nearest facts in response to the input text. Since the fact, consisting of only two entities and one relation, has little context to encode, we propose to further refine ranks of top-k retrieved facts with a reranker that contextualizes the input text and the fact jointly. We validate our DiFaR framework on multiple fact retrieval tasks, showing that it significantly outperforms relevant baselines that use the three-step approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baek-etal-2023-direct">
<titleInfo>
<title>Direct Fact Retrieval from Knowledge Graphs without Entity Linking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinheon</namePart>
<namePart type="family">Baek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jens</namePart>
<namePart type="family">Lehmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sung</namePart>
<namePart type="given">Ju</namePart>
<namePart type="family">Hwang</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 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>There has been a surge of interest in utilizing Knowledge Graphs (KGs) for various natural language processing/understanding tasks. The conventional mechanism to retrieve facts in KGs usually involves three steps: entity span detection, entity disambiguation, and relation classification. However, this approach requires additional labels for training each of the three subcomponents in addition to pairs of input texts and facts, and also may accumulate errors propagated from failures in previous steps. To tackle these limitations, we propose a simple knowledge retrieval framework, which directly retrieves facts from the KGs given the input text based on their representational similarities, which we refer to as Direct Fact Retrieval (DiFaR). Specifically, we first embed all facts in KGs onto a dense embedding space by using a language model trained by only pairs of input texts and facts, and then provide the nearest facts in response to the input text. Since the fact, consisting of only two entities and one relation, has little context to encode, we propose to further refine ranks of top-k retrieved facts with a reranker that contextualizes the input text and the fact jointly. We validate our DiFaR framework on multiple fact retrieval tasks, showing that it significantly outperforms relevant baselines that use the three-step approach.</abstract>
<identifier type="citekey">baek-etal-2023-direct</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.558</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.558</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>10038</start>
<end>10055</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Direct Fact Retrieval from Knowledge Graphs without Entity Linking
%A Baek, Jinheon
%A Aji, Alham Fikri
%A Lehmann, Jens
%A Hwang, Sung Ju
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F baek-etal-2023-direct
%X There has been a surge of interest in utilizing Knowledge Graphs (KGs) for various natural language processing/understanding tasks. The conventional mechanism to retrieve facts in KGs usually involves three steps: entity span detection, entity disambiguation, and relation classification. However, this approach requires additional labels for training each of the three subcomponents in addition to pairs of input texts and facts, and also may accumulate errors propagated from failures in previous steps. To tackle these limitations, we propose a simple knowledge retrieval framework, which directly retrieves facts from the KGs given the input text based on their representational similarities, which we refer to as Direct Fact Retrieval (DiFaR). Specifically, we first embed all facts in KGs onto a dense embedding space by using a language model trained by only pairs of input texts and facts, and then provide the nearest facts in response to the input text. Since the fact, consisting of only two entities and one relation, has little context to encode, we propose to further refine ranks of top-k retrieved facts with a reranker that contextualizes the input text and the fact jointly. We validate our DiFaR framework on multiple fact retrieval tasks, showing that it significantly outperforms relevant baselines that use the three-step approach.
%R 10.18653/v1/2023.acl-long.558
%U https://aclanthology.org/2023.acl-long.558
%U https://doi.org/10.18653/v1/2023.acl-long.558
%P 10038-10055
Markdown (Informal)
[Direct Fact Retrieval from Knowledge Graphs without Entity Linking](https://aclanthology.org/2023.acl-long.558) (Baek et al., ACL 2023)
ACL
- Jinheon Baek, Alham Fikri Aji, Jens Lehmann, and Sung Ju Hwang. 2023. Direct Fact Retrieval from Knowledge Graphs without Entity Linking. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10038–10055, Toronto, Canada. Association for Computational Linguistics.