An Investigation of Recurrent Neural Architectures for Drug Name Recognition

TL;DR

This paper evaluates recurrent neural network architectures for drug name recognition in biomedical texts, demonstrating that bidirectional LSTM-CRF models perform comparably to traditional hand-crafted systems.

Contribution

It investigates the effectiveness of modern recurrent neural architectures for DNR, highlighting the potential of neural models to replace handcrafted feature-based methods.

Findings

Bidirectional LSTM-CRF achieves performance close to specialized systems.

Recurrent neural architectures can effectively perform DNR from raw text.

Neural models reduce reliance on domain-specific feature engineering.

Abstract

Drug name recognition (DNR) is an essential step in the Pharmacovigilance (PV) pipeline. DNR aims to find drug name mentions in unstructured biomedical texts and classify them into predefined categories. State-of-the-art DNR approaches heavily rely on hand crafted features and domain specific resources which are difficult to collect and tune. For this reason, this paper investigates the effectiveness of contemporary recurrent neural architectures - the Elman and Jordan networks and the bidirectional LSTM with CRF decoding - at performing DNR straight from the text. The experimental results achieved on the authoritative SemEval-2013 Task 9.1 benchmarks show that the bidirectional LSTM-CRF ranks closely to highly-dedicated, hand-crafted systems.