Joint relational triple extraction based on potential relation detection and conditional entity mapping

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 53; no. 24; pp. 29656 - 29676
• Main Authors: Zhou, Xiong, Zhang, Qinghua, Gao, Man, Wang, Guoyin
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.12.2023; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Science; Information retrieval; Knowledge representation; Machines; Manufacturing; Mapping; Mechanical Engineering; Modules; Processes; Semantic relations; Semantics; Sentences; Teaching methods; Words (language); Entity mapping; Joint relational triple extraction; Conditional layer normalization; Potential relation detection
• DOI: 10.1007/s10489-023-05111-4
• ISSN: 0924-669X

Joint relational triple extraction treats entity recognition and relation extraction as a joint task to extract relational triples, and this is a critical task in information extraction and knowledge graph construction. However, most existing joint models still fall short in terms of extracting overlapping triples. Moreover, these models ignore the trigger words of potential relations during the relation detection process. To address the two issues, a joint model based on P otential R elation D etection and C onditional E ntity M apping is proposed, named PRDCEM. Specifically, the proposed model consists of three components, i.e., potential relation detection, candidate entity tagging, and conditional entity mapping, corresponding to three subtasks. First, a non-autoregressive decoder that contains a cross-attention mechanism is applied to detect potential relations. In this way, different potential relations are associated with the corresponding trigger words in the given sentence, and the semantic representations of the trigger words are fully utilized to encode potential relations. Second, two distinct sequence taggers are employed to extract candidate subjects and objects. Third, an entity mapping module incorporating conditional layer normalization is designed to align the candidate subjects and objects. As such, each candidate subject and each potential relation are combined to form a condition that is incorporated into the sentence, which can effectively extract overlapping triples. Finally, the negative sampling strategy is employed in the entity mapping module to mitigate the error propagation from the previous two components. In a comparison with 15 baselines, the experimental results obtained on two widely used public datasets demonstrate that PRDCEM can effectively extract overlapping triples and achieve improved performance.