Syntactic and Semantic-driven Learning for Open Information Extraction

by   Jialong Tang, et al.

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


page 1

page 2

page 3

page 4


Syntactic Scaffolds for Semantic Structures

We introduce the syntactic scaffold, an approach to incorporating syntac...

How to best use Syntax in Semantic Role Labelling

There are many different ways in which external information might be use...

Neural Open Information Extraction

Conventional Open Information Extraction (Open IE) systems are usually b...

Using a Diathesis Model for Semantic Parsing

This paper presents a semantic parsing approach for unrestricted texts. ...

Neural Transition-based Syntactic Linearization

The task of linearization is to find a grammatical order given a set of ...

Building a Semantic Role Labelling System for Vietnamese

Semantic role labelling (SRL) is a task in natural language processing w...

Countering Language Drift with Seeded Iterated Learning

Supervised learning methods excel at capturing statistical properties of...