The Referential Reader: A Recurrent Entity Network for Anaphora Resolution

By Fei Liu, Luke S. Zettlemoyer, Jacob Eisenstein. 2019

19 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems (2019, methodology): “The outside results for COPA, MultiRC, and RTE are from Sap et al. (2019), Trivedi et al. (2019), and Liu et al. (2019c) respectively.”
Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs (2022, background): “work has shown that training entity-centric neural architectures on text with entity coreference information yields more entity-aware LLMs, both in recurrent (Henaff et al., 2017; Ji et al., 2017; Yang et al., 2017; Liu et al., 2019) and Transformerbased models (Févry et al.”
Pre-training of Mention Representations in Coreference Models (2020, methodology): “Liu et al. (2019) uses a language model objective to train a memory network, which can resolve coreference links.”
BERT for Coreference Resolution: Baselines and Analysis (2019, background): “More recently, advances in coreference resolution and other NLP tasks have been driven by unsupervised contextualized representations (Peters et al., 2018; Devlin et al., 2019; McCann et al., 2017; Joshi et al., 2019; Liu et al., 2019b).”
WikiCREM: A Large Unsupervised Corpus for Coreference Resolution (2019, methodology): “We find nouns in the premise with the Stanford POS tagger (Manning et al., 2014).”
Gendered Ambiguous Pronouns Shared Task: Boosting Model Confidence by Evidence Pooling (2019, methodology): “The performance of ProBERT and GREP models is benchmarked against results previously established by Webster et al. and Liu et al. (2019).”