Injecting Categorical Labels and Syntactic Information into Biomedical NER

TL;DR

This paper proposes a method to enhance biomedical NER by injecting categorical labels and syntactic POS information, using sentence classification and joint learning, leading to improved performance over baseline models.

Contribution

Introduces a novel approach to incorporate categorical labels and POS tags into biomedical NER models through sentence classification and joint learning methods.

Findings

Outperforms baseline BERT-based models on benchmark datasets.

Effective representation and injection of labels and POS tags improve NER accuracy.

Joint learning of labels and NER enhances syntactic and categorical context understanding.

Abstract

We present a simple approach to improve biomedical named entity recognition (NER) by injecting categorical labels and Part-of-speech (POS) information into the model. We use two approaches, in the first approach, we first train a sequence-level classifier to classify the sentences into categories to obtain the sentence-level tags (categorical labels). The sequence classifier is modeled as an entailment problem by modifying the labels as a natural language template. This helps to improve the accuracy of the classifier. Further, this label information is injected into the NER model. In this paper, we demonstrate effective ways to represent and inject these labels and POS attributes into the NER model. In the second approach, we jointly learn the categorical labels and NER labels. Here we also inject the POS tags into the model to increase the syntactic context of the model. Experiments on three benchmark datasets show that incorporating categorical label information with syntactic context is quite useful and outperforms baseline BERT-based models.