Conditional Knowledge Extraction Using Contextual Information Enhancement

• Published in: Applied sciences 2023-04, Vol.13 (8), p.4954
• Main Authors: Xu, Zhangbiao, Zhang, Botao, Gu, Jinguang, Gao, Feng
• Format: Article
• Language: English
• Subjects: Artificial intelligence; conditional knowledge graph; Domains; information matching; Information retrieval; Knowledge representation; Neural networks; phrase extraction; pre-training model; Semantics
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app13084954

Conditional phrases provide fine-grained domain knowledge in various industries, including medicine, manufacturing, and others. Most existing knowledge extraction research focuses on mining triplets with entities and relations and treats that triplet knowledge as plain facts without considering the conditional modality of such facts. We argue that such approaches are insufficient in building knowledge-based decision support systems in vertical domains, where specific and professional instructions on what facts apply under given circumstances are indispensable. To address this issue, this paper proposes a condition-aware knowledge extraction method using contextual information. In particular, this paper first fine-tunes the pre-training model to leverage a local context enhancement to capture the positional context of conditional phrases; then, a sentence-level context enhancement is used to integrate sentence semantics; finally, the correspondences between conditional phrases and relation triplets are extracted using syntactic attention. Experimental results on public and proprietary datasets show that our model can successfully retrieve conditional phrases with relevant triplets while improving the accuracy of the matching task by 2.68%, compared to the baseline.