An Instance Transfer based Approach Using Enhanced Recurrent Neural Network for Domain Named Entity Recognition

TL;DR

This paper introduces an enhanced RNN model with an instance transfer strategy to improve domain-specific named entity recognition, especially when target domain labeled data is scarce, by leveraging similar source domain data.

Contribution

The paper proposes a novel enhanced RNN architecture and an instance transfer method for effective domain adaptation in NER tasks.

Findings

Enhanced RNN outperforms traditional RNN, HMM, and CRF in NER.

Instance transfer significantly improves F1 scores in low-resource target domains.

The approach achieves up to 15.76% improvement in F1 measure over direct source data use.

Abstract

Recently, neural networks have shown promising results for named entity recognition (NER), which needs a number of labeled data to for model training. When meeting a new domain (target domain) for NER, there is no or a few labeled data, which makes domain NER much more difficult. As NER has been researched for a long time, some similar domain already has well labelled data (source domain). Therefore, in this paper, we focus on domain NER by studying how to utilize the labelled data from such similar source domain for the new target domain. We design a kernel function based instance transfer strategy by getting similar labelled sentences from a source domain. Moreover, we propose an enhanced recurrent neural network (ERNN) by adding an additional layer that combines the source domain labelled data into traditional RNN structure. Comprehensive experiments are conducted on two datasets. The comparison results among HMM, CRF and RNN show that RNN performs bette than others. When there is no labelled data in domain target, compared to directly using the source domain labelled data without selecting transferred instances, our enhanced RNN approach gets improvement from 0.8052 to 0.9328 in terms of F1 measure.