NLNDE: Enhancing Neural Sequence Taggers with Attention and Noisy Channel for Robust Pharmacological Entity Detection
This work addresses the challenge of named entity recognition in specialized domains and languages, specifically for pharmacological entities in Spanish, representing an incremental improvement with practical applications in biomedical text mining.
The paper tackled pharmacological entity detection in Spanish texts, a non-standard domain and language setting, by proposing an architecture that requires no language or domain expertise, achieving up to 88.6% F1 score in a competition.
Named entity recognition has been extensively studied on English news texts. However, the transfer to other domains and languages is still a challenging problem. In this paper, we describe the system with which we participated in the first subtrack of the PharmaCoNER competition of the BioNLP Open Shared Tasks 2019. Aiming at pharmacological entity detection in Spanish texts, the task provides a non-standard domain and language setting. However, we propose an architecture that requires neither language nor domain expertise. We treat the task as a sequence labeling task and experiment with attention-based embedding selection and the training on automatically annotated data to further improve our system's performance. Our system achieves promising results, especially by combining the different techniques, and reaches up to 88.6% F1 in the competition.