Syntactically Robust Training on Partially-Observed Data for Open Information Extraction

TL;DR

This paper introduces a training framework for Open Information Extraction models that enhances syntactic robustness by using paraphrase generation and knowledge restoration techniques, validated on a new diverse dataset.

Contribution

It proposes a novel syntactically robust training method with algorithms for knowledge restoration, applicable to real-world syntactic diversity in data.

Findings

Models degrade with increasing syntactic difference.

The proposed framework maintains robustness across diverse syntactic distributions.

A new dataset CaRB-AutoPara validates the approach.

Abstract

Open Information Extraction models have shown promising results with sufficient supervision. However, these models face a fundamental challenge that the syntactic distribution of training data is partially observable in comparison to the real world. In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation. To tackle the intrinsic problem of knowledge deformation of paraphrasing, two algorithms based on semantic similarity matching and syntactic tree walking are used to restore the expressionally transformed knowledge. The training framework can be generally applied to other syntactic partial observable domains. Based on the proposed framework, we build a new evaluation set called CaRB-AutoPara, a syntactically diverse dataset consistent with the real-world setting for validating the robustness of the models. Experiments including a thorough analysis show that the performance of the model degrades with the increase of the difference in syntactic distribution, while our framework gives a robust boundary. The source code is publicly available at https://github.com/qijimrc/RobustOIE.