Information Retrieval and Two-Directional Word Formation
Arvi Hurskainen · DOAJ (DOAJ: Directory of Open Access Journals) · 1995
This paper presents some applications of SWATWOL, a morphological parser of Swahili, for information retrieval. It presents a solution to the problem of retrieving accurate linguistic information in a language, where word formation branches out from the lemma to both directions. After discussing technical problems and their solution, some research tasks that have been carried out, or which are in process, are described. Among those are: testing dictionaries, retrieval of loan words from running text, word?form distribution of lemmas, and total distribution of words (counted according to lemmas) in different types of text. The obviously most important application is the production of a database for dictionary compilers, with a selection of contexts of use for each lemma.