LEMMATIZATION OF ENGLISH VERBS IN COMPOUND TENSES

In general, lemmatization is performed on verbs conjugated by means of suffixes, that is, on simple verbs. In English, we have lemmas and paradigms such as: to work: work, works, worked, working to eat: eat, eats, ate, eaten, eating But, there is no reason why forms composed of an auxiliary verb and a non finite verb such as is working or has eaten should not be part of these paradigms and lemmatized accordingly; after all, they are full-fledged conjugated forms. From the point of view of parsing, there is a difficulty in recognizing compound tenses, because inserts may occur between their parts: Jo is today working on an essay Bob has not much eaten Hence, inserts have to be recognized in order to bring together the parts of a compound verb. 1. Inserts Inserts are of various types, ranging from simple adverbs to complex combinations of adverbial phrases; some of these phrases can be sentential, in which case, their length is unbounded and their analysis requires the full power of a sentence parser. Nonetheless, it is possible to construct detailed grammars for most adverbial phrases and a study of corpora by C. Fairon 1999 has shown that the number of compound verbs which are 'disrupted ' by inserts is small and that moreover long inserts occur in texts quite rarely