# A Joint Named-Entity Recognizer for Heterogeneous Tag-sets Using a Tag Hierarchy

## TL;DR

This paper introduces a neural network model that leverages a tag hierarchy to jointly recognize named entities across heterogeneous and partially overlapping annotation schemes, improving performance in domain adaptation scenarios.

## Contribution

It proposes a novel joint learning approach using tag hierarchies for NER across diverse datasets, outperforming independent and multitask models.

## Key findings

- Tag-hierarchy model outperforms independent models.
- Model effectively consolidates heterogeneous tag-sets.
- Improves NER performance in domain adaptation settings.

## Abstract

We study a variant of domain adaptation for named-entity recognition where multiple, heterogeneously tagged training sets are available. Furthermore, the test tag-set is not identical to any individual training tag-set. Yet, the relations between all tags are provided in a tag hierarchy, covering the test tags as a combination of training tags. This setting occurs when various datasets are created using different annotation schemes. This is also the case of extending a tag-set with a new tag by annotating only the new tag in a new dataset. We propose to use the given tag hierarchy to jointly learn a neural network that shares its tagging layer among all tag-sets. We compare this model to combining independent models and to a model based on the multitasking approach. Our experiments show the benefit of the tag-hierarchy model, especially when facing non-trivial consolidation of tag-sets.