# Nested and Balanced Entity Recognition using Multi-Task Learning

arXiv: https://arxiv.org/abs/2106.06216 · HTML: https://mlsanity.com/paper/2106.06216/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Builds on (most cited first, 11 of 11)

- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [A Unified MRC Framework for Named Entity Recognition](https://mlsanity.com/paper/1910.11476/) (2019)
- [Dice Loss for Data-imbalanced NLP Tasks](https://mlsanity.com/paper/1911.02855/) (2019)
- [Neural Architectures for Nested NER through Linearization](https://mlsanity.com/paper/1908.06926/) (2019)
- [Nested Named Entity Recognition via Second-best Sequence Learning and Decoding](https://mlsanity.com/paper/1909.02250/) (2019)
- [Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks](https://mlsanity.com/paper/1906.03783/) (2019)
- [Hierarchical Contextualized Representation for Named Entity Recognition](https://mlsanity.com/paper/1911.02257/) (2019)
- [Dependency-Guided LSTM-CRF for Named Entity Recognition](https://mlsanity.com/paper/1909.10148/) (2019)
- [Bipartite Flat-Graph Network for Nested Named Entity Recognition](https://mlsanity.com/paper/2005.00436/) (2020)
- [Adaptive Name Entity Recognition under Highly Unbalanced Data](https://mlsanity.com/paper/2003.10296/) (2020)

## Abstract (arXiv)

Entity Recognition (ER) within a text is a fundamental exercise in Natural Language Processing, enabling further depending tasks such as Knowledge Extraction, Text Summarisation, or Keyphrase Extraction. An entity consists of single words or of a consecutive sequence of terms, constituting the basic building blocks for communication. Mainstream ER approaches are mainly limited to flat structures, concentrating on the outermost entities while ignoring the inner ones. This paper introduces a partly-layered network architecture that deals with the complexity of overlapping and nested cases. The proposed architecture consists of two parts: (1) a shared Sequence Layer and (2) a stacked component with multiple Tagging Layers. The adoption of such an architecture has the advantage of preventing overfit to a specific word-length, thus maintaining performance for longer entities despite their lower frequency. To verify the proposed architecture's effectiveness, we train and evaluate this architecture to recognise two kinds of entities - Concepts (CR) and Named Entities (NER). Our approach achieves state-of-the-art NER performances, while it outperforms previous CR approaches. Considering these promising results, we see the possibility to evolve the architecture for other cases such as the extraction of events or the detection of argumentative components.