A Framework for Enriching Lexical Semantic Resources with Distributional Semantics

TL;DR

This paper introduces a hybrid semantic resource that combines distributional semantics from text with manually crafted lexical networks, improving knowledge acquisition and disambiguation tasks.

Contribution

It presents a novel framework for aligning distributional semantic representations with lexical ontologies to create high-quality, enriched semantic resources.

Findings

High-quality hybrid resource achieved through automatic disambiguation and alignment.

Manual and extrinsic evaluations demonstrate the resource's effectiveness.

Enrichment improves hypernym graph cleaning and taxonomy learning.

Abstract

We present an approach to combining distributional semantic representations induced from text corpora with manually constructed lexical-semantic networks. While both kinds of semantic resources are available with high lexical coverage, our aligned resource combines the domain specificity and availability of contextual information from distributional models with the conciseness and high quality of manually crafted lexical networks. We start with a distributional representation of induced senses of vocabulary terms, which are accompanied with rich context information given by related lexical items. We then automatically disambiguate such representations to obtain a full-fledged proto-conceptualization, i.e. a typed graph of induced word senses. In a final step, this proto-conceptualization is aligned to a lexical ontology, resulting in a hybrid aligned resource. Moreover, unmapped induced senses are associated with a semantic type in order to connect them to the core resource. Manual evaluations against ground-truth judgments for different stages of our method as well as an extrinsic evaluation on a knowledge-based Word Sense Disambiguation benchmark all indicate the high quality of the new hybrid resource. Additionally, we show the benefits of enriching top-down lexical knowledge resources with bottom-up distributional information from text for addressing high-end knowledge acquisition tasks such as cleaning hypernym graphs and learning taxonomies from scratch.