Monolingual alignment of word senses and definitions in lexicographical resources

TL;DR

This paper develops methods for aligning monolingual lexicographical data, creating a benchmark for evaluation, and extending the work to translation inference, aiding resource creation for under-resourced languages.

Contribution

Introduces a new benchmark for monolingual word sense alignment and proposes methods for translation inference using graph analysis, with practical tool implementation.

Findings

Benchmark contains 17 datasets across 15 languages.

Alignment techniques show varying performance on the benchmark.

Unsupervised translation inference improves lexicon coverage for low-resource languages.

Abstract

The focus of this thesis is broadly on the alignment of lexicographical data, particularly dictionaries. In order to tackle some of the challenges in this field, two main tasks of word sense alignment and translation inference are addressed. The first task aims to find an optimal alignment given the sense definitions of a headword in two different monolingual dictionaries. This is a challenging task, especially due to differences in sense granularity, coverage and description in two resources. After describing the characteristics of various lexical semantic resources, we introduce a benchmark containing 17 datasets of 15 languages where monolingual word senses and definitions are manually annotated across different resources by experts. In the creation of the benchmark, lexicographers' knowledge is incorporated through the annotations where a semantic relation, namely exact, narrower, broader, related or none, is selected for each sense pair. This benchmark can be used for evaluation purposes of word-sense alignment systems. The performance of a few alignment techniques based on textual and non-textual semantic similarity detection and semantic relation induction is evaluated using the benchmark. Finally, we extend this work to translation inference where translation pairs are induced to generate bilingual lexicons in an unsupervised way using various approaches based on graph analysis. This task is of particular interest for the creation of lexicographical resources for less-resourced and under-represented languages and also, assists in increasing coverage of the existing resources. From a practical point of view, the techniques and methods that are developed in this thesis are implemented within a tool that can facilitate the alignment task.