# Efficient Seq2seq Coreference Resolution Using Entity Representations

arXiv: https://arxiv.org/abs/2510.14504 · HTML: https://mlsanity.com/paper/2510.14504/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 25 of 25)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference](https://mlsanity.com/paper/2403.09636/) (2024)
- [Coreference Resolution as Query-based Span Prediction](https://mlsanity.com/paper/1911.01746/) (2019)
- [Isambard-AI: a leadership class supercomputer optimised specifically for Artificial Intelligence](https://mlsanity.com/paper/2410.11199/) (2024)
- [An Annotated Dataset of Coreference in English Literature](https://mlsanity.com/paper/1912.01140/) (2019)
- [Coreference Resolution without Span Representations](https://mlsanity.com/paper/2101.00434/) (2021)
- [Autoregressive Structured Prediction with Language Models](https://mlsanity.com/paper/2210.14698/) (2022)
- [Word-Level Coreference Resolution](https://mlsanity.com/paper/2109.04127/) (2021)
- [Coreference Resolution through a seq2seq Transition-Based System](https://mlsanity.com/paper/2211.12142/) (2022)
- [Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks](https://mlsanity.com/paper/2010.02807/) (2020)
- [LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution](https://mlsanity.com/paper/2205.12644/) (2022)
- [On Generalization in Coreference Resolution](https://mlsanity.com/paper/2109.09667/) (2021)
- [Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends](https://mlsanity.com/paper/2407.21489/) (2024)
- [Moving on from OntoNotes: Coreference Resolution Model Transfer](https://mlsanity.com/paper/2104.08457/) (2021)
- [2 * n is better than n2: Decomposing Event Coreference Resolution into Two Tractable Problems](https://mlsanity.com/paper/2305.05672/) (2023)
- [A Cluster Ranking Model for Full Anaphora Resolution](https://mlsanity.com/paper/1911.09532/) (2019)
- [Sequential Cross-Document Coreference Resolution](https://mlsanity.com/paper/2104.08413/) (2021)
- [Improving Generalization in Coreference Resolution via Adversarial Training](https://mlsanity.com/paper/1908.04728/) (2019)
- [Seq2seq is All You Need for Coreference Resolution](https://mlsanity.com/paper/2310.13774/) (2023)
- [Online Coreference Resolution for Dialogue Processing: Improving Mention-Linking on Real-Time Conversations](https://mlsanity.com/paper/2205.10670/) (2022)

## Abstract (arXiv)

Seq2seq coreference models have introduced a new paradigm for coreference resolution by learning to generate text corresponding to coreference labels, without requiring task-specific parameters. While these models achieve new state-of-the-art performance, they do so at the cost of flexibility and efficiency. In particular, they do not efficiently handle incremental settings such as dialogue, where text must processed sequentially. We propose a compressed representation in order to improve the efficiency of these methods in incremental settings. Our method works by extracting and re-organizing entity-level tokens, and discarding the majority of other input tokens. On OntoNotes, our best model achieves just 0.6 CoNLL F1 points below a full-prefix, incremental baseline while achieving a compression ratio of 1.8. On LitBank, where singleton mentions are annotated, it passes state-of-the-art performance. Our results indicate that discarding a wide portion of tokens in seq2seq resolvers is a feasible strategy for incremental coreference resolution.