Structural Linguistics and Unsupervised Information Extraction

摘要

A precondition for extracting information from large text corpora is discovering the information structures underlying the text. Progress in this direction is being made in the form of unsupervised information extraction (IE). We describe recent work in unsupervised relation extraction and compare its goals to those of grammar discovery for science sublanguages. We consider what this work on grammar discovery suggests for future directions in unsupervised IE.