A Simple but Effective Bidirectional Framework for Relational Triple Extraction

@article{Ren2022ASB,
  title={A Simple but Effective Bidirectional Framework for Relational Triple Extraction},
  author={Feiliang Ren and Longhui Zhang and Xiaofeng Zhao and Shujuan Yin and Shilei Liu and Bochao Li},
  journal={Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining},
  year={2022}
}
  • Feiliang Ren, Longhui Zhang, Bochao Li
  • Published 9 December 2021
  • Computer Science
  • Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
Tagging based relational triple extraction methods are attracting growing research attention recently. However, most of these methods take a unidirectional extraction framework that first extracts all subjects and then extracts objects and relations simultaneously based on the subjects extracted. This framework has an obvious deficiency that it is too sensitive to the extraction results of subjects. To overcome this deficiency, we propose a bidirectional extraction framework based method that… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 36 REFERENCES
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
TLDR
A fresh perspective to revisit the relational triple extraction task is introduced and a novel cascade binary tagging framework (CasRel) derived from a principled problem formulation is proposed, which naturally handles the overlapping problem.
Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy
TLDR
This paper decomposes the joint extraction task into two interrelated subtasks, namely HE extraction and TER extraction, and deconstructed into several sequence labeling problems based on the proposed span-based tagging scheme, which are conveniently solved by a hierarchical boundary tagger and a multi-span decoding algorithm.
Creating Training Corpora for NLG Micro-Planners
TLDR
This paper proposes the corpus generation framework as a novel method for creating challenging data sets from which NLG models can be learned which are capable of handling the complex interactions occurring during in micro-planning between lexicalisation, aggregation, surface realisation, referring expression generation and sentence segmentation.
PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction
TLDR
A component to predict potential relations is designed, which constrains the following entity extraction to the predicted relation subset rather than all relations; then a relation-specific sequence tagging component is applied to handle the overlapping problem between subjects and objects; finally, a global correspondence component is designed to align the subject and object into a triple with low-complexity.
Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer Network
TLDR
A unified framework to jointly extract explicit and implicit relational triples and introduce real-world relational reasoning patterns in the model and capture these patterns with a relation network is proposed.
TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking
TLDR
This paper proposes a one-stage joint extraction model, namely, TPLinker, which is capable of discovering overlapping relations sharing one or both entities while being immune from the exposure bias, and formulates joint extraction as a token pair linking problem and introduces a novel handshaking tagging scheme.
Modeling Relations and Their Mentions without Labeled Text
TLDR
A novel approach to distant supervision that can alleviate the problem of noisy patterns that hurt precision by using a factor graph and applying constraint-driven semi-supervision to train this model without any knowledge about which sentences express the relations in the authors' training KB.
Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations
TLDR
A novel approach for multi-instance learning with overlapping relations that combines a sentence-level extraction model with a simple, corpus-level component for aggregating the individual facts is presented.
Progressive Multitask Learning with Controlled Information Flow for Joint Entity and Relation Extraction. In Association for the Advancement of Artificial Intelligence (AAAI)
  • 2021
StereoRel: Relational Triple Extraction from a Stereoscopic Perspective
TLDR
A novel model is proposed for relational triple extraction, which maps relational triples to a three-dimension (3-D) space and leverages three decoders to extract them, aimed at simultaneously handling the above issues.
...
...