Syntactic and Semantic-driven Learning for Open Information Extraction

TL;DR

This paper introduces a novel syntactic and semantic-driven learning method for open information extraction that eliminates the need for labeled data by leveraging linguistic knowledge and reinforcement learning, achieving high accuracy.

Contribution

It presents a new approach combining syntactic patterns and reinforcement learning to train open IE models without labeled data, outperforming supervised methods.

Findings

Outperforms supervised models in accuracy

Achieves competitive results with state-of-the-art models

Eliminates reliance on labeled training data

Abstract

One of the biggest bottlenecks in building accurate, high coverage neural open IE systems is the need for large labelled corpora. The diversity of open domain corpora and the variety of natural language expressions further exacerbate this problem. In this paper, we propose a syntactic and semantic-driven learning approach, which can learn neural open IE models without any human-labelled data by leveraging syntactic and semantic knowledge as noisier, higher-level supervisions. Specifically, we first employ syntactic patterns as data labelling functions and pretrain a base model using the generated labels. Then we propose a syntactic and semantic-driven reinforcement learning algorithm, which can effectively generalize the base model to open situations with high accuracy. Experimental results show that our approach significantly outperforms the supervised counterparts, and can even achieve competitive performance to supervised state-of-the-art (SoA) model