The connection between part-of-speech (POS) categories and morphological properties is well-documented in linguistics but underutilized in text processing systems. This paper proposes a novel model for morphological segmentation that is driven by this connection. Our model learns that words with common affixes are likely to be in the same syntactic category and uses learned syntactic categories...

Résumé. Dans cet article nous détaillons une approche permettant de détecter des affixes et des termes déclencheurs à partir de dictionnaires de façon automatique en se basant sur l’algorithme de la plus longue sous-chaîne commune, dans le cadre de la reconnaissance d’entités nommées chimiques sur CHEMDNER. Nous verrons ensuite des méthodes de sélection et de tri afin de les intégrer au mieux d...

In this paper, we contrast English and Greek resultative secondary predication, showing that Greek lacks the productive syntactic strategy which English employs. We propose that the difference in productivity should be attributed to properties of the morphology in the two languages (namely, to the differing productivity of certain verbal affixes). Finally, we give a compositional semantics for ...

Phrases has a long history in information retrieval, particularly in commercial systems. Implicit semantic relationship between words in a form of BaseNP have shown significant improvement in term of precision in many IR studies. Our research focuses on linguistic phrases which is language dependent. Our results show that using BaseNP can improve performance although above 62% of words formatio...

Laz spatial adverbs are notional lexical items making up rather numerous and semantically diverse groups. They play a significant role in linguistic representation of structures determining which circumstances with what features an action, conveyed by verb, proceeds. satellites outside verb stem; sentences, they occur as adverbial modifiers convey space-related information: direction movement p...

This study investigates functional interpretations of left anterior negativities (LANs), a language-related electroencephalogram effect that has been found for syntactic and morphological violations. We focus on three possible interpretations of LANs caused by the replacement of irregular affixes with regular affixes: misapplication of morphological rules, mismatch of the presented form with an...

We present a partially new fully unsupervised algorithm for morphological segmentation of a arbitrary natural language with only one-slot concatenative morphology. The behaviour of the algorithm is examined in detail for Indonesian as it is a good approximation of such a language. The underlying theory makes no assumptions on whether the language is prefixing or suffixing, or whether affixes ar...

A system for recognition and morphological classification of unknown words for German is described and evaluated. It takes raw text as input and outputs a list of the unknown nouns together with a hypothesis about their possible morphological class and stem. MorphoClass exploits global information (ending-guessing rules, maximum likelihood estimations, word frequency statistics), morphological ...