Multi-Round Parsing-based Multiword Rules for Scientific OpenIE

TL;DR

This paper introduces a rule-based approach using dependency parsing for scientific OpenIE, effectively extracting multiword relations without requiring annotated training data, demonstrated on new datasets.

Contribution

The work presents a novel multi-round parsing-based rule system for scientific OpenIE that operates without annotated training data, addressing multiword expression boundary detection.

Findings

Effective extraction of multiword relations in scientific texts

No need for annotated training data

Demonstrated on novel datasets

Abstract

Information extraction (IE) in scientific literature has facilitated many down-stream tasks. OpenIE, which does not require any relation schema but identifies a relational phrase to describe the relationship between a subject and an object, is being a trending topic of IE in sciences. The subjects, objects, and relations are often multiword expressions, which brings challenges for methods to identify the boundaries of the expressions given very limited or even no training data. In this work, we present a set of rules for extracting structured information based on dependency parsing that can be applied to any scientific dataset requiring no expert's annotation. Results on novel datasets show the effectiveness of the proposed method. We discuss negative results as well.