# FlexNER: A Flexible LSTM-CNN Stack Framework for Named Entity Recognition

## TL;DR

FlexNER introduces a versatile NER framework that enhances entity-context diversity without external resources, improving performance across multiple languages and domains through flexible layer stacking and sub-network combinations.

## Contribution

The paper proposes a novel flexible LSTM-CNN stack framework for NER that adapts to various languages and domains without external resources.

## Key findings

- Effective across five languages including English, German, Spanish, Dutch, and Chinese.
- Successfully applied to biomedical NER tasks like chemicals and gene/protein recognition.
- Demonstrates strong performance in diverse datasets.

## Abstract

Named entity recognition (NER) is a foundational technology for information extraction. This paper presents a flexible NER framework compatible with different languages and domains. Inspired by the idea of distant supervision (DS), this paper enhances the representation by increasing the entity-context diversity without relying on external resources. We choose different layer stacks and sub-network combinations to construct the bilateral networks. This strategy can generally improve model performance on different datasets. We conduct experiments on five languages, such as English, German, Spanish, Dutch and Chinese, and biomedical fields, such as identifying the chemicals and gene/protein terms from scientific works. Experimental results demonstrate the good performance of this framework.