A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
Новая каскадная бинарная модель разметки для извлечения реляционных троек
2020-01-01
SCID: 54.1/xrka34ak
Discuss with AI
BERT encodercascade binary taggingknowledge graph constructionoverlapping triplesrelational triple extraction
Figures from the paper
Abstract (AI)
Extracting relational triples from unstructured text is crucial for large-scale knowledge graph construction.However, few existing works excel in solving the overlapping triple problem where multiple relational triples in the same sentence share the same entities.In this work, we introduce a fresh perspective to revisit the relational triple extraction task and propose a novel cascade binary tagging framework (CASREL) derived from a principled problem formulation.Instead of treating relations as discrete labels as in previous works, our new framework models relations as functions that map subjects to objects in a sentence, which naturally handles the overlapping problem.Experiments show that the CAS-REL framework already outperforms state-ofthe-art methods even when its encoder module uses a randomly initialized BERT encoder, showing the power of the new tagging framework.It enjoys further performance boost when employing a pre-trained BERT encoder, outperforming the strongest baseline by 17.5 and 30.2 absolute gain in F1-score on two public datasets NYT and WebNLG, respectively.In-depth analysis on different scenarios of overlapping triples shows that the method delivers consistent performance gain across all these scenarios.The source code and data are released online 1 .
Key Findings
1
Analysis across different overlapping-triple scenarios shows consistent performance gains, and the authors release the source code and data.
2
CASREL introduces a cascade binary tagging framework that models relations as subject-to-object functions rather than discrete labels.
3
CASREL outperforms state-of-the-art methods even with a randomly initialized BERT encoder, demonstrating the effectiveness of its tagging formulation.
4
The framework naturally addresses overlapping relational triples, including cases where multiple triples share entities within a sentence.
5
Using a pre-trained BERT encoder, CASREL exceeds the strongest baseline by 17.5 and 30.2 absolute F1 points on NYT and WebNLG, respectively.
Research Object
relational triples in unstructured text
Research Subject
overlapping-triple extraction, particularly the handling of multiple triples sharing entities
Publication Details
Publication Date
2020-01-01
Journal
Publisher
ISSN
Cited by
714
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
Adam: A Method for Stochastic Optimization2014
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation2016
Data Driven VRP: A Neural Network Model to Learn Hidden Preferences for VRP2021
Qualitative Spatial Reasoning over Questions (Short Paper)2022