A Multi-task Learning Approach for Named Entity Recognition using Local Detection

TL;DR

This paper introduces a multi-task learning model for NER that uses local detection and fixed-size sequence representations, achieving competitive results across multiple datasets.

Contribution

The paper proposes a novel locally detecting multi-task model with fixed-size sequence encoding for improved NER performance.

Findings

Achieved competitive performance on multiple NER datasets.

Demonstrated the effectiveness of fixed-size sequence representations.

Compared favorably to baseline and published models.

Abstract

Named entity recognition (NER) systems that perform well require task-related and manually annotated datasets. However, they are expensive to develop, and are thus limited in size. As there already exists a large number of NER datasets that share a certain degree of relationship but differ in content, it is important to explore the question of whether such datasets can be combined as a simple method for improving NER performance. To investigate this, we developed a novel locally detecting multitask model using FFNNs. The model relies on encoding variable-length sequences of words into theoretically lossless and unique fixed-size representations. We applied this method to several well-known NER tasks and compared the results of our model to baseline models as well as other published results. As a result, we observed competitive performance in nearly all of the tasks.