ACL Findings2021
KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction
Abhishek Nadgeri, Anson Bastos, Kuldeep Singh, Isaiah Onando Mulang', Johannes Hoffart, Saeedeh Shekarpour, Vijay Saraswat
Abstract
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on3
- Relational Message Passing for Knowledge Graph CompletionHongwei Wang, Hongyu Ren, Jure LeskovecKDD 2021 · 109 citations
- RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural NetworkAnson Bastos, Abhishek Nadgeri, Kuldeep Singh, Isaiah Onando Mulang' et al.WWW 2021 · 92 citations
- Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement LearningXiaomian Kang, Yang Zhao, Jiajun Zhang, Chengqing ZongEMNLP 2020 · 61 citations
Related papers
- Improving Neural Relation Extraction with Implicit Mutual RelationsJun Kuang, Yixin Cao, Jianbing Zheng, Xiangnan He et al.ICDE 2020 · 24 citations
- Complex Factoid Question Answering with a Free-Text Knowledge GraphChen Zhao, Chenyan Xiong, Xin Qian, Jordan L. Boyd-GraberWWW 2020 · 39 citations
- KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph CompletionZhaoxuan Tan, Zilong Chen, Shangbin Feng, Qingyue Zhang et al.WWW 2023 · 50 citations
- Context-aware Entity Typing in Knowledge GraphsWeiran Pan, Wei Wei, Xian-Ling MaoEMNLP Findings 2021 · 33 citations
- Re-Temp: Relation-Aware Temporal Representation Learning for Temporal Knowledge Graph CompletionKunze Wang, Soyeon Caren Han, Josiah PoonEMNLP Findings 2023 · 17 citations
