# Improving Chemical Named Entity Recognition in Patents with Contextualized Word Embeddings

## TL;DR

This paper demonstrates that using contextualized ELMo embeddings and domain-specific resources significantly enhances chemical named entity recognition accuracy in patent documents, addressing the complexity of patent language.

## Contribution

It introduces a BiLSTM-CRF model leveraging contextualized ELMo embeddings and domain-specific resources for improved chemical NER in patents, outperforming previous methods.

## Key findings

- ELMo embeddings substantially improve NER performance.
- Domain-specific word embeddings and tokenizers positively impact results.
- The approach outperforms current state-of-the-art methods.

## Abstract

Chemical patents are an important resource for chemical information. However, few chemical Named Entity Recognition (NER) systems have been evaluated on patent documents, due in part to their structural and linguistic complexity. In this paper, we explore the NER performance of a BiLSTM-CRF model utilising pre-trained word embeddings, character-level word representations and contextualized ELMo word representations for chemical patents. We compare word embeddings pre-trained on biomedical and chemical patent corpora. The effect of tokenizers optimized for the chemical domain on NER performance in chemical patents is also explored. The results on two patent corpora show that contextualized word representations generated from ELMo substantially improve chemical NER performance w.r.t. the current state-of-the-art. We also show that domain-specific resources such as word embeddings trained on chemical patents and chemical-specific tokenizers have a positive impact on NER performance.