Lessons from Natural Language Inference in the Clinical Domain

Abstract

State of the art models using deep neural networks have become very good in learning an accurate mapping from inputs to outputs. However, they still lack generalization capabilities in conditions that differ from the ones encountered during training. This is even more challenging in specialized, and knowledge intensive domains, where training data is limited. To address this gap, we introduce MedNLI - a dataset annotated by doctors, performing a natural language inference task (NLI), grounded in the medical history of patients. We present strategies to: 1) leverage transfer learning using datasets from the open domain, (e.g. SNLI) and 2) incorporate domain knowledge from external data and lexical sources (e.g. medical terminologies). Our results demonstrate performance gains using both strategies.

arXiv commentExtended version of the EMNLP 2018 paper. Dataset and code available at https://jgc128.github.io/mednli/

References in corpus (7)

• Scikit-learn: Machine Learning in Python
• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Enhanced LSTM for Natural Language Inference
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• A large annotated corpus for learning natural language inference
• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
• Learned in Translation: Contextualized Word Vectors

Cited by in corpus (8)

• SciFive: a text-to-text transformer model for biomedical literature
• Probing Biomedical Embeddings from Language Models
• Membership Inference Attack Susceptibility of Clinical Language Models
• A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports
• A Hybrid Approach to Measure Semantic Relatedness in Biomedical Concepts
• Learning Conceptual-Contextual Embeddings for Medical Text
• Benchmarking BioRelEx for Entity Tagging and Relation Extraction
• Pentagon at MEDIQA 2019: Multi-task Learning for Filtering and Re-ranking Answers using Language Inference and Question Entailment