arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08457cs.CL
收藏

从OntoNotes继续:共指消解模型转换

Moving on from OntoNotes: Coreference Resolution Model Transfer

Johns Hopkins University(约翰斯·霍普金斯大学)

Patrick Xia, Benjamin Van Durme

摘要:

用于共指消解(coref)的学术神经模型通常在单个数据集OntoNotes上进行训练,并且模型改进在同一数据集上进行基准测试。然而,coref的实际应用取决于注释指南和目标数据集的域,这通常与OntoNotes不同。我们的目标是根据目标数据集中可用的注释文档的数量来量化coref模型的可移植性。我们检查了11个目标数据集,发现持续训练是一贯有效的,特别是在目标文档很少的情况下。我们在多个数据集上建立了新的基准,包括PreCo的最新结果。

英文摘要:

Academic neural models for coreference resolution (coref) are typically trained on a single dataset, OntoNotes, and model improvements are benchmarked on that same dataset. However, real-world applications of coref depend on the annotation guidelines and the domain of the target dataset, which often differ from those of OntoNotes. We aim to quantify transferability of coref models based on the number of annotated documents available in the target dataset. We examine eleven target datasets and find that continued training is consistently effective and especially beneficial when there are few target documents. We establish new benchmarks across several datasets, including state-of-the-art results on PreCo.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑