We propose a sentence-incremental neural coreference resolution system which
incrementally builds clusters after marking mention boundaries in a
shift-reduce method. The system is aimed at bridging two recent approaches at
coreference resolution: (1) state-of-the-art non-incremental models that incur
quadratic complexity in document length with high computational cost, and (2)
memory network-based models which operate incrementally but do not generalize
beyond pronouns. For comparison, we simulate an incremental setting by
constraining non-incremental systems to form partial coreference chains before
observing new sentences. In this setting, our system outperforms comparable
state-of-the-art methods by 2 F1 on OntoNotes and 7 F1 on the CODI-CRAC 2021
corpus. In a conventional coreference setup, our system achieves 76.3 F1 on
OntoNotes and 45.8 F1 on CODI-CRAC 2021, which is comparable to
state-of-the-art baselines. We also analyze variations of our system and show
that the degree of incrementality in the encoder has a surprisingly large
effect on the resulting performance.

本文提出一种句子增量神经代词消解系统，成功地融合了两种最新的技术：非增量模型和内存网络模型，在 OntoNotes 和 CODI-CRAC 2021 中达到了更好的结果。

句子级递增神经共指消解

Sentence-Incremental Neural Coreference Resolution

We apply BERT to coreference resolution, achieving strong improvements on the
OntoNotes (+3.9 F1) and GAP (+11.5 F1) benchmarks. A qualitative analysis of
model predictions indicates that, compared to ELMo and BERT-base, BERT-large is
particularly better at distinguishing between related but distinct entities
(e.g., President and CEO). However, there is still room for improvement in
modeling document-level context, conversations, and mention paraphrasing. Our
code and models are publicly available.

本文利用 BERT 模型对共指消解问题进行了研究，结果表明利用 BERT 模型在 OntoNotes 和 GAP 基准上取得了显著提升。自行搭建模型的测试结果表明，相比 ELMo 和 BERT-base 模型，BERT-large 模型在区分相关实体上表现更好，但在建模文档上下文、对话以及提取意象的方面，还有进一步提高的空间。