Open Information Extraction (OIE) aims to extract relational tuples from open-domain sentences. Existing OIE systems split a sentence into tokens and recognize token spans as tuple relations and arguments. We instead propose Sentence as Chunk sequence (SaC) and recognize chunk spans as tuple relations and arguments. We argue that SaC has better quantitative and qualitative properties for OIE than sentence as token sequence, and evaluate four choices of chunks (i.e., CoNLL chunks, simple phrases, NP chunks, and spans from SpanOIE) against gold OIE tuples. Accordingly, we propose a simple BERT-based model for sentence chunking, and propose Chunk-OIE for tuple extraction on top of SaC. Chunk-OIE achieves state-of-the-art results on multiple OIE datasets, showing that SaC benefits OIE task.

翻译：开放信息抽取（Open Information Extraction, OIE）旨在从开放域句子中提取关系元组。现有OIE系统将句子切分为词元，并识别词元跨度作为元组关系和论元。本文相反地提出"句子即块序列"（Sentence as Chunk sequence, SaC）方法，将块跨度识别为元组关系和论元。我们论证，相较于"句子即词元序列"方法，SaC在定量与定性维度上均具备更优的OIE特性，并通过对比四种块选择方案（即CoNLL块、简单短语、NP块及SpanOIE跨度）与基准OIE元组验证该结论。据此，我们提出基于BERT的简洁句子分块模型，并基于SaC框架构建Chunk-OIE元组抽取系统。Chunk-OIE在多个OIE数据集上达到最优性能，证实SaC对OIE任务具有显著助益。