Document-level Entity-based Extraction as Template Generation

EMNLP 2021  ·  Kung-Hsiang Huang, Sam Tang, Nanyun Peng ·

Document-level entity-based extraction (EE), aiming at extracting entity-centric information such as entity roles and entity relations, is key to automatic knowledge acquisition from text corpora for various domains. Most document-level EE systems build extractive models, which struggle to model long-term dependencies among entities at the document level. To address this issue, we propose a generative framework for two document-level EE tasks: role-filler entity extraction (REE) and relation extraction (RE). We first formulate them as a template generation problem, allowing models to efficiently capture cross-entity dependencies, exploit label semantics, and avoid the exponential computation complexity of identifying N-ary relations. A novel cross-attention guided copy mechanism, TopK Copy, is incorporated into a pre-trained sequence-to-sequence model to enhance the capabilities of identifying key information in the input document. Experiments done on the MUC-4 and SciREX dataset show new state-of-the-art results on REE (+3.26%), binary RE (+4.8%), and 4-ary RE (+2.7%) in F1 score.

PDF Abstract EMNLP 2021 PDF EMNLP 2021 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Role-filler Entity Extraction MUC-4 TempGen Avg. F1 57.76 # 1
4-ary Relation Extraction SciREX TempGen Avg. F1 3.55 # 1
Binary Relation Extraction SciREX TempGen Avg. F1 14.47 # 1