In statistical machine translation, correspondences between the words in the source and the target language are learned from parallel corpora, and often little or no linguistic knowledge is used to structure the underlying models. In particular, existing statistical systems for machine translation often treat different inflected forms of the same lemma as if they were independent of one another...

In the framework of statistical machine translation, correspondences between the words in the source and the target language are learned from bilingual corpora, and often little or no linguistic knowledge is used to structure the underlying models. The work presented in this thesis is motivated by the well-known observation that training data typically does not sufficiently represent the range ...

We present the first results in the development of a multilingual resource that should enable the exploration of the possibility to apply various different lexical bases, such as edictionaries in LADL format and multilingual lexical databases like Wordnet and Prolex that were developed during the last decade. We discuss the problems of morphosyntactic annotation of the phenomena of regular deri...

This thesis improves unsupervised methods for part-of-speech (POS) induction and morphological word segmentation by modeling linguistic phenomena previously not used. For both tasks, we realize these linguistic intuitions with Bayesian generative models that first create a latent lexicon before generating unannotated tokens in the input corpus. Our POS induction model explicitly incorporates pr...

Within current surface-oriented lexical frameworks, the standard approach to cliticization phenomena in Romance assumes that affixation of pronominal clitics to their verbal hosts should be conceived of as an instance of lexical alternation. Consequently, under the analyses proposed by e.g. Miller and Sag (1995) and Monachesi (1996) these phenomena are dealt with in terms of lexical rules. This...

Morphological analysis and disambiguation are crucial stages in a variety of natural language processing applications such as machine translation, especially when languages with complex morphology are concerned such as Arabic. Arabic is a highly flexional language, in that, the same root can lead to various forms according to its context. In this paper, we present a system which disambiguates t...

The study provides an original standpoint of the speech transcription errors by focusing on the morpho-syntactic features of the erroneous chunks and of the surrounding left and right context. The typology concerns the forms, the lemmas and the POS involved in erroneous chunks, and in the surrounding contexts. Comparison with error free contexts are also provided. The study is conducted on Fren...

We present an experimental study making use of a machine learning approach to identify the factors that affect the aspectual value that characterises polysemous verbs under each of their readings. The study is based on various morpho-syntactic and semantic features collected from a French lexical resource and on a gold standard aspectual classification of verb readings designed by an expert. Ou...

A morpho-syntactic tagger associates to each word of a corpus a label which recapitulates its morpho-syntatic properties in the text. In corpora from oral data, not only do we have to face the usual problem of multi-labels words, but also the more specific problems of disfluences (repetitions, ungrammatical constructions...), of non existing words and of the lack of punctuation marks [1]. First...

For the treatment of agreement in Dutch NPs I adopt a distinction, familiar from HPSG, between morphosyntactic agreement and index agreement. In order to determine their respective roles, I make another distinction, proposed in Van Eynde (2003), between marked and unmarked nominals. Employing these distinctions, I will demonstrate that the combination of prenominal adjectives and determiners wi...