A temporal expression recognition system for medical documents by

A bottleneck for medical domain Temporal Expression Recognition (TER) is the availability of data. An open-domain TER system may not be able to capture domain-specific expressions, while domain-specific TER may be cumbersome to implement. We present a novel neural network based medical TER system that uses corpora from news and medical domains. Thus, it serves as a middle ground between an open-domain and a domain-specific TER. We show that our system outperforms state-of-art open-domain baselines, and gets close to domain-specific skylines. Thus, our system proves to be a promising alternative for domain specific TER for domains where data may be limited.