HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction

Text-to-Graph extraction aims to automatically extract information graphs consisting of mentions and types from natural language texts. Existing approaches, such as table filling and pairwise scoring, have shown impressive performance on various information extraction tasks, but they are difficult to scale to datasets with longer input texts because of their second-order space/time complexities with respect to the input length. In this work, we propose a Hybrid Span Generator (HySPA) that invertibly maps the information graph to an alternating sequence of nodes and edge types, and directly generates such sequences via a hybrid span decoder which can decode both the spans and the types recurrently in linear time and space complexities. Extensive experiments on the ACE05 dataset show that our approach also significantly outperforms state-of-the-art on the joint entity and relation extraction task.

PDF Abstract Findings (ACL) 2021 PDF Findings (ACL) 2021 Abstract

Datasets


Results from the Paper


 Ranked #1 on Relation Extraction on ACE 2005 (Sentence Encoder metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction ACE 2005 HySPA Sentence Encoder ALBERT # 1
Cross Sentence No # 1
Relation Extraction ACE 2005 HySPA (ours) w/ RoBERTa Relation F1 68.2 # 1

Methods


No methods listed for this paper. Add relevant methods here