While coreference resolution is defined independently of dataset domain, most models for
performing coreference resolution do not transfer well to unseen domains. We consolidate a …

We consider the end-to-end abstract-to-title generation problem, exploring seven recent
transformer based models (including ChatGPT) fine-tuned on more than 30k abstract-title …

In this paper, we provide an overview of the CODI-CRAC 2021 Shared-Task: Anaphora
Resolution in Dialogue. The shared task focuses on detecting anaphoric relations in …

Abstract The CODI-CRAC 2022 Shared Task on Anaphora Resolution in Dialogues is the
second edition of an initiative focused on detecting different types of anaphoric relations in …

Despite recent advances in Natural Language Processing (NLP), hierarchical discourse
parsing in the framework of Rhetorical Structure Theory remains challenging, and our …

Coreference resolution models are often evaluated on multiple datasets. Datasets vary,
however, in how coreference is realized--ie, how the theoretical concept of coreference is …

It is increasingly common to evaluate the same coreference resolution (CR) model on
multiple datasets. Do these multi-dataset evaluations allow us to draw meaningful …

We present GENTLE, a new mixed-genre English challenge corpus totaling 17K tokens and
consisting of 8 unusual text types for out-of domain evaluation: dictionary entries, esports …

All state-of-the-art coreference resolution (CR) models involve finetuning a pretrained
language model. Whether the superior performance of one CR model over another is due to …

The limited generalization of coreference resolution (CR) models has been a major
bottleneck in the task's broad application. Prior work has identified annotation differences …