SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining
arXiv:2108.08983
Abstract
Recently, the performance of Pre-trained Language Models (PLMs) has been significantly improved by injecting knowledge facts to enhance their abilities of language understanding. For medical domains, the background knowledge sources are especially useful, due to the massive medical terms and their complicated relations are difficult to understand in text. In this work, we introduce SMedBERT, a medical PLM trained on large-scale medical corpora, incorporating deep structured semantic knowledge from neighbors of linked-entity.In SMedBERT, the mention-neighbor hybrid attention is proposed to learn heterogeneous-entity information, which infuses the semantic representations of entity types into the homogeneous neighboring entity structure. Apart from knowledge integration as external features, we propose to employ the neighbors of linked-entities in the knowledge graph as additional global contexts of text mentions, allowing them to communicate via shared neighbors, thus enrich their semantic representations. Experiments demonstrate that SMedBERT significantly outperforms strong baselines in various knowledge-intensive Chinese medical tasks. It also improves the performance of other tasks such as question answering, question matching and natural language inference.
arXiv commentACL2021
References in corpus (11)
- Efficient Estimation of Word Representations in Vector Space
- Distributed Representations of Words and Phrases and their Compositionality
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- Gaussian Error Linear Units (GELUs)
- Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
- Pre-trained Models for Natural Language Processing: A Survey
- ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission
- Conceptualized Representation Learning for Chinese Biomedical Text Mining
- Neighborhood Mixture Model for Knowledge Base Completion
- CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model
- E-BERT: A Phrase and Product Knowledge Enhanced Language Model for E-commerce