# The Referential Reader: A Recurrent Entity Network for Anaphora Resolution

arXiv: https://arxiv.org/abs/1902.01541 · HTML: https://mlsanity.com/paper/1902.01541/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2019.

## Built on by (most cited first, 8 of 8)

- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Model](https://mlsanity.com/paper/2305.10845/) (2023)
- [RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution](https://mlsanity.com/paper/2309.04977/) (2023)
- [Online Coreference Resolution for Dialogue Processing: Improving Mention-Linking on Real-Time Conversations](https://mlsanity.com/paper/2205.10670/) (2022)
- [A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information](https://mlsanity.com/paper/2305.07565/) (2023)
- [Sentence-Incremental Neural Coreference Resolution](https://mlsanity.com/paper/2305.16947/) (2023)
- [A Sequence-to-Sequence Approach for Arabic Pronoun Resolution](https://mlsanity.com/paper/2305.11529/) (2023)
- [What's the Point? Spatial Grammar & Index Resolution for Sign Language Processing](https://mlsanity.com/paper/2606.08056/) (2026)

## Abstract (arXiv)

We present a new architecture for storing and accessing entity mentions during online text processing. While reading the text, entity references are identified, and may be stored by either updating or overwriting a cell in a fixed-length memory. The update operation implies coreference with the other mentions that are stored in the same cell; the overwrite operation causes these mentions to be forgotten. By encoding the memory operations as differentiable gates, it is possible to train the model end-to-end, using both a supervised anaphora resolution objective as well as a supplementary language modeling objective. Evaluation on a dataset of pronoun-name anaphora demonstrates strong performance with purely incremental text processing.