期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：634-644
DOI：10.18653/v1/2021.eacl-main.52
语种：English
出版社：ACL Anthology
摘要：We revisit the classic problem of document-level role-filler entity extraction (REE) for template filling. We argue that sentence-level approaches are ill-suited to the task and introduce a generative transformer-based encoder-decoder framework (GRIT) that is designed to model context at the document level: it can make extraction decisions across sentence boundaries; is implicitly aware of noun phrase coreference structure, and has the capacity to respect cross-role dependencies in the template structure. We evaluate our approach on the MUC-4 dataset, and show that our model performs substantially better than prior work. We also show that our modeling choices contribute to model performance, e.g., by implicitly capturing linguistic knowledge such as recognizing coreferent entity mentions.
