Abstract
The paper presents an unsupervised method for quickly extending a Ukrainian lexicon by generating paradigms and morphological feature structures for new Named Entities and neologisms, which are not covered by existing static morphological resources. This approach addresses a practical problem of modelling paradigms for entities created by the dynamic processes in the lexicon: this problem is especially serious for highly-inflected languages in domains with specialised or quickly changing lexicon. The method uses an unannotated Ukrainian corpus and a small fixed set of inflection tables, which can be found in traditional grammar textbooks. The advantage of the proposed approach is that updating the morphological lexicon does not require training or linguistic annotation, allowing fast knowledge-light extension of an existing static lexicon to improve morphological coverage on a specific corpus. The method is implemented in an open-source package on a GitHub repository. It can be applied to other low-resourced inflectional languages which have internet corpora and linguistic descriptions of their inflection system, following the example of inflection tables for Ukrainian. Evaluation results shows consistent improvements in coverage for Ukrainian corpora of different corpus types.
Highlights
"Our language can be regarded as an ancient city: a maze of little streets and squares, of old and new houses, of houses with extensions from various periods, and all this surrounded by a multitude of new suburbs with straight and regular streets and uniform houses." (Wittgenstein, 2009)
Even though there may be many irregularities in the lexicon, similar to ‘a maze of little streets’, this more often happens with an older lexical core, while new words typically follow more ‘straight and regular’ patterns, so the task of updating the lexicon for natural language applications may be facilitated by this tendency
This paper investigates the extent of the new lexicon problem for different types of Ukrainian corpora and further proposes and evaluates a knowledge-light approach to extending lexical coverage of morphological resources to neologisms and new single-word Named Entities which follow regular inflectional patterns
Summary
"Our language can be regarded as an ancient city: a maze of little streets and squares, of old and new houses, of houses with extensions from various periods, and all this surrounded by a multitude of new suburbs with straight and regular streets and uniform houses." (Wittgenstein, 2009). The approach proposed in this paper is designed for the scenario where for a highly-inflected language there exists a hand-crafted static morphological lexicon that covers potentially irregular and more frequent lexical core For extending this lexicon to cover new regularly inflected entities I use an internet corpus and small inflection tables from grammar textbooks, e.g., (Hryshchenko et al, 1997), (Press and Pugh, 2015): such resources would often be available for other lowresourced languages, since the tasks that would require linguistic expertise (i.e., creating the core lexicon and inflection tables) need to be done only once, so paradigms for new entities can be automatically created whenever a new corpus becomes available.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
