Text tagging is a very important tool for various applications in natural language processing, namely the morphological and syntactic analysis of texts, indexation and information retrieval, "vocalization" of Arabic texts, and probabilistic language model (n-class model). However, these systems based on the lexemes of limited size, are unable to treat unknown words consequently. To overcome thi...

In this work, we examine and attempt to extend the coverage of a German HPSG grammar. We use the grammar to parse a corpus of newspaper text and evaluate the proportion of sentences which have a correct attested parse, and analyse the cause of errors in terms of lexical or constructional gaps which prevent parsing. Then, using a maximum entropy model, we evaluate prediction of lexical types in ...

The domain of lexical combinatorics has received much interest over the last years, in syntax, lexical semantics and lexicology, but also in lexicography, terminology, terminography and in Natural Language Processing (NLP). If the field of combinatorics can maybe trivially be defined by the fact that it deals with syntagmatic combination phenomena involving two or more lexemes, it is much harde...

A model of the identification of information tonality, based on Bayesian approach and neural networks was described. In the context of this paper tonality means positive or negative tone of both the whole information and its parts which are related to particular concepts. The method, its application is presented in the paper, is based on statistic regularities connected with the presence of def...

In this paper we discuss the problem of building the Polish lexicon for the Cyc ontology. As the ontology is very large and complex we describe semi-automatic translation of part of it, which might be useful for tasks lying on the border between the fields of Semantic Web and Natural Language Processing. We concentrate on precise identification of lexemes, which is crucial for tasks such as nat...

Most multi-word lexemes (MWLs) allow certain types of variation. This has to be taken into account for their description and their recognition in texts. We suggest to describe their syntactic restrictions and their idiosyncratic peculiarities with local grammar rules, which at the same time allow to express in a general way regularities valid for a whole class of MWLs. The local grammars can be...

Functional Arabic Morphology is a formulation of the Arabic inflectional system seeking the working interface between morphology and syntax. ElixirFM is its high-level implementation that reuses and extends the Functional Morphology library for Haskell. Inflection and derivation are modeled in terms of paradigms, grammatical categories, lexemes and word classes. The computation of analysis or g...

This paper presents a new language-independent method for finding morphological links between newly appeared words (i.e. absent from reference word lists). Using the WWW as a corpus, the Webaffix tool detects the occurrences of new derived lexemes based on a given suffix, proposes a base lexeme following a standard scheme (such as noun-verb), and then performs a compatibility test on the word p...

The system utilizes a Recognizing Textual Entailment (RTE) approach. The system uses the question string (q_str) as a Text (T) and one answer (t_str) as a Hypothesis (H). We use two different approaches using machine learning, specifically Support Vector Machine as classifier. The results show an increment over the baselines, however enhanced is needed. The features used are unigram, bigram, an...

This paper presents the modelling of Proper Name domain defined by the Prolex project. This modelling is based on two main concepts: the Conceptual Proper Name and the Prolexeme. The Conceptual Proper Name do not represents the referent, but a point of view on this referent. It has a specific concept in each language, the Prolexeme, that is a structured family of lexemes. Around them, we have d...