Bootstrapping Deep Lexical Resources: Resources for Courses

TL;DR

This paper introduces deep lexical acquisition methods leveraging morphological, syntactic, and ontological resources to bootstrap lexical items, analyzing their effectiveness and resource accessibility for improving lexical resources.

Contribution

It presents novel methods for deep lexical acquisition using diverse language resources and evaluates their strengths, weaknesses, and resource efficiency.

Findings

Different methods excel with different word classes.

Resource type impacts acquisition effectiveness.

Morphological, syntactic, and ontological resources vary in accessibility.

Abstract

We propose a range of deep lexical acquisition methods which make use of morphological, syntactic and ontological language resources to model word similarity and bootstrap from a seed lexicon. The different methods are deployed in learning lexical items for a precision grammar, and shown to each have strengths and weaknesses over different word classes. A particular focus of this paper is the relative accessibility of different language resource types, and predicted ``bang for the buck'' associated with each in deep lexical acquisition applications.