Monolingual alignment of word senses and definitions in lexicographical resources

Ahmadi, Sina
Dictionaries are fundamental resources for people to learn and document languages as well as for computers to process natural languages. A dictionary provides a fine-grained structure and description of the vocabulary of a language. With decades of advances in electronic lexicography, a significant amount of lexicographical resources are currently available. Such resources are the fruits of elaborate and strenuous efforts of lexicographers and oftentimes, are costly projects to initiate and maintain. Moreover, given the increasing number of lexical semantic resources, thanks to community-driven initiatives such as Wiktionary, the alignment of such resources is of importance to promote interoperability and increase their exploitation more effectively. On the other hand, the significant progress in the field of computer science, artificial intelligence and the semantic web has been tremendously beneficial to various scientific fields, particularly language technology. Therefore, there is an opportunity to leverage the current techniques and resources to facilitate the automatic alignment, integration and enrichment of lexicographical data. 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.
NUI Galway
Publisher DOI
Attribution-NonCommercial-NoDerivs 3.0 Ireland