Automatic extraction of paraphrastic phrases from medium size corpora

TL;DR

This paper introduces a system that automatically extracts paraphrastic phrases from medium-sized corpora using machine learning and semantic networks to facilitate NLP resource creation.

Contribution

It presents a novel method for automatically deriving paraphrastic templates and resources from text corpora, reducing manual effort in NLP system development.

Findings

Automated extraction of paraphrastic phrases demonstrated.

System integrates machine learning with semantic networks.

Reduces resource creation time for NLP applications.

Abstract

This paper presents a versatile system intended to acquire paraphrastic phrases from a representative corpus. In order to decrease the time spent on the elaboration of resources for NLP system (for example Information Extraction, IE hereafter), we suggest to use a machine learning system that helps defining new templates and associated resources. This knowledge is automatically derived from the text collection, in interaction with a large semantic network.