A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
By Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang. Annual Meeting of the Association for Computational Linguistics, 2019
655 citations recorded by the source corpus.
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 CasRel framework already outperforms state-of-the-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.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/76fd100c9776f9d42c61618f31df7a33a6ffda00
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Unified Named Entity Recognition as Word-Word Relation Classification (2021, background): “…fundamental task in natural language processing (NLP) community, due to its wide variety of knowledge-based applications, e.g., relation extraction (Wei et al. 2020; Li et al. 2021b), entity linking (Le and Titov 2018; Hou et al. 2020), etc. Studies of NER have gradually evolved initially from the…”
- A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “[171] proposed a cascade binary tagging framework that models relations as subject-object mapping functions to solve the overlapping problem.”
- BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining (2022, methodology): “Sequence labeling methods tackle the task by labeling the word tokens in the text with different tags to mark out all the entity mentions and then perform the relation classification between them via classifiers [35, 36, 37, 38].”
- Zero-Shot Information Extraction via Chatting with ChatGPT (2023, background): “…information from unstructured text into structured data formats, including tasks such as entity-relation triple extract (RE), named entity recognition (NER), event extraction (EE) (Tjong Kim Sang, 2002; Ratinov and Roth, 2009; Wei et al., 2020; Zheng et al., 2021; Li et al., 2020a), etc .”
- Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction (2021, background): “Recently, pre-trained language models (De-vlin et al., 2019) have also been extensively used in RE tasks (Wu and He, 2019; Wei et al., 2020; Baldini Soares et al., 2019), and have achieved state-of-the-arts performance.”
- TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking (2020, methodology): “(Wei et al., 2020) except for ETL-Span, of which the results are reproduced by the official implementation.”