We present Contextual Discourse Vectors (CDV), a distributed document representation for efficient answer retrieval from long healthcare documents. Our approach is based on structured query tuples of entities and aspects from free text and medical taxonomies. Our model leverages a dual encoder architecture with hierarchical LSTM layers and multi-task training to encode the position of clinical entities and aspects alongside the document discourse. We use our continuous representations to resolve queries with short latency using approximate nearest neighbor search on sentence level. We apply the CDV model for retrieving coherent answer passages from nine English public health resources from the Web, addressing both patients and medical professionals. Because there is no end-to-end training data available for all application scenarios, we train our model with self-supervised data from Wikipedia. We show that our generalized model significantly outperforms several state-of-the-art baselines for healthcare passage ranking and is able to adapt to heterogeneous domains without additional fine-tuning.
- Jens-Michalis Papaioannou, Manuel Mayrdorfer, Sebastian Arnold, Felix A. Gers, Klemens Budde and Alexander Löser: Aspect-based Passage Retrieval with Contextualized Discourse Vectors, Proceedings of the 43rd European Conference on Information Retrieval ECIR 2021
- Sebastian Arnold, Betty van Aken, Paul Grundmann, Felix A. Gers and Alexander Löser. Learning Contextualized Document Representations for Healthcare Answer Retrieval.The Web Conference 2020 (WWW'20). ACM, 2020: 1332–1343 [code] [PDF].