# Neural Mention Detection

arXiv: https://arxiv.org/abs/1907.12524 · HTML: https://mlsanity.com/paper/1907.12524/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2019.

## Built on by (most cited first, 6 of 6)

- [TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases](https://mlsanity.com/paper/2210.12925/) (2022)
- [Transformers as Graph-to-Graph Models](https://mlsanity.com/paper/2310.17936/) (2023)
- [End-to-end Neural Information Status Classification](https://mlsanity.com/paper/2109.02753/) (2021)
- [A Structured Span Selector](https://mlsanity.com/paper/2205.03977/) (2022)
- [SPLICE: A Singleton-Enhanced PipeLIne for Coreference REsolution](https://mlsanity.com/paper/2403.17245/) (2024)
- [Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models](https://mlsanity.com/paper/2506.21294/) (2025)

## Abstract (arXiv)

Mention detection is an important preprocessing step for annotation and interpretation in applications such as NER and coreference resolution, but few stand-alone neural models have been proposed able to handle the full range of mentions. In this work, we propose and compare three neural network-based approaches to mention detection. The first approach is based on the mention detection part of a state of the art coreference resolution system; the second uses ELMO embeddings together with a bidirectional LSTM and a biaffine classifier; the third approach uses the recently introduced BERT model. Our best model (using a biaffine classifier) achieves gains of up to 1.8 percentage points on mention recall when compared with a strong baseline in a HIGH RECALL coreference annotation setting. The same model achieves improvements of up to 5.3 and 6.2 p.p. when compared with the best-reported mention detection F1 on the CONLL and CRAC coreference data sets respectively in a HIGH F1 annotation setting. We then evaluate our models for coreference resolution by using mentions predicted by our best model in start-of-the-art coreference systems. The enhanced model achieved absolute improvements of up to 1.7 and 0.7 p.p. when compared with our strong baseline systems (pipeline system and end-to-end system) respectively. For nested NER, the evaluation of our model on the GENIA corpora shows that our model matches or outperforms state-of-the-art models despite not being specifically designed for this task.