KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction

Nadgeri, A. and Bastos, A. and Singh, K. and et al, . (2021) KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 1 August 2021 through 6 August 2021, Virtual, Online.

[img] Text
ACL_IJCNLP_2021.pdf - Published Version
Restricted to Registered users only

Download (851kB) | Request a copy


We present a novel method for relation extraction (RE) from a single sentence, mapping the sentence and two given entities to a canonical fact in a knowledge graph (KG). Especially in this presumed sentential RE setting, the context of a single sentence is often sparse. This paper introduces the KGPool method to address this sparsity, dynamically expanding the context with additional facts from the KG. It learns the representation of these facts (entity alias, entity descriptions, etc.) using neural methods, supplementing the sentential context. Unlike existing methods that statically use all expanded facts, KGPool conditions this expansion on the sentence. We study the efficacy of KGPool by evaluating it with different neural models and KGs (Wikidata and NYT Freebase). Our experimental evaluation on standard datasets shows that by feeding the KGPool representation into a Graph Neural Network, the overall method is significantly more accurate than state-of-the-art methods. © 2021 Association for Computational Linguistics

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Condition; Experimental evaluation; Graph neural networks; Knowledge graphs; Learn+; Neural modelling; Novel methods; Relation extraction; State-of-the-art methods
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 02 Sep 2022 05:14
Last Modified: 02 Sep 2022 05:14
Publisher URL:
Related URLs:

    Actions (login required)

    View Item View Item
    Statistics for RAIITH ePrint 10388 Statistics for this ePrint Item