Detect and Classify – Joint Span Detection and Classification for Health Outcomes
Micheal Abaho, Danushka Bollegala, Paula Williamson, Susanna Dodd
Abstract
A health outcome is a measurement or an observation used to capture and assess the effect of a treatment. Automatic detection of health outcomes from text would undoubtedly speed up access to evidence necessary in healthcare decision making. Prior work on outcome detection has modelled this task as either (a) a sequence labelling task, where the goal is to detect which text spans describe health outcomes, or (b) a classification task, where the goal is to classify a text into a predefined set of categories depending on an outcome that is mentioned somewhere in that text. However, this decoupling of span detection and classification is problematic from a modelling perspective and ignores global structural correspondences between sentence-level and word-level information present in a given text. To address this, we propose a method that uses both word-level and sentence-level information to simultaneously perform outcome span detection and outcome type classification. In addition to injecting contextual information to hidden vectors, we use label attention to appropriately weight both word and sentence level information. Experimental results on several benchmark datasets for health outcome detection show that our proposed method consistently outperforms decoupled methods, reporting competitive results.- Anthology ID:
- 2021.emnlp-main.686
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8709–8721
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.686
- DOI:
- 10.18653/v1/2021.emnlp-main.686
- Cite (ACL):
- Micheal Abaho, Danushka Bollegala, Paula Williamson, and Susanna Dodd. 2021. Detect and Classify – Joint Span Detection and Classification for Health Outcomes. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8709–8721, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Detect and Classify – Joint Span Detection and Classification for Health Outcomes (Abaho et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2021.emnlp-main.686.pdf
- Code
- MichealAbaho/Label-Context-Aware-Attention-Model
- Data
- EBM-NLP