Wrap-Up: a Trainable Discourse Module for Information Extraction

TL;DR

This paper introduces Wrap-Up, a trainable discourse module for information extraction that automatically learns classifiers and features, enabling higher-level inference in unrestricted text with performance comparable to manually customized systems.

Contribution

The paper presents a fully trainable IE discourse component that automatically determines classifiers and features, advancing beyond previous limited, lower-level processing approaches.

Findings

Performance matches manually customized modules

Automatically derives classifiers and features

Enables higher-level inferences in IE systems

Abstract

The vast amounts of on-line text now available have led to renewed interest in information extraction (IE) systems that analyze unrestricted text, producing a structured representation of selected information from the text. This paper presents a novel approach that uses machine learning to acquire knowledge for some of the higher level IE processing. Wrap-Up is a trainable IE discourse component that makes intersentential inferences and identifies logical relations among information extracted from the text. Previous corpus-based approaches were limited to lower level processing such as part-of-speech tagging, lexical disambiguation, and dictionary construction. Wrap-Up is fully trainable, and not only automatically decides what classifiers are needed, but even derives the feature set for each classifier automatically. Performance equals that of a partially trainable discourse module requiring manual customization for each domain.