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

arXiv: https://arxiv.org/abs/1905.09135 · HTML: https://mlsanity.com/paper/1905.09135/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2019.

## Built on by (most cited first, 4 of 4)

- [Named Entity Recognition and Classification on Historical Documents: A Survey](https://mlsanity.com/paper/2109.11406/) (2021)
- [Cross-Domain Label-Adaptive Stance Detection](https://mlsanity.com/paper/2104.07467/) (2021)
- [Few-shot Named Entity Recognition with Self-describing Networks](https://mlsanity.com/paper/2203.12252/) (2022)
- [Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks](https://mlsanity.com/paper/2111.01340/) (2021)

## Abstract (arXiv)

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.