Abstract. We present a novel approach to incorporating semantic information to the problems of natural language processing, in particular to the document classification task. The ...
Filip Ginter, Sampo Pyysalo, Jorma Boberg, Jouni J...
Word fragments or n-grams have been widely used to perform different Natural Language Processing tasks such as information retrieval [1] [2], document categorization [3], automatic...
We describe a proposal on spelling correction intended to be applied on Galician, a Romance language. Our aim is to put into evidence the flexibility of a novelty technique that p...
Manuel Vilares Ferro, Juan Otero, Francisco-Mario ...
Abstract. This paper describes two procedures for generating very short summaries for documents from the DUC-2003 competition: a chunk extraction method based on syntactic dependen...
This paper presents an algorithm to apply the smoothing techniques described in [1] to three different Machine Learning (ML) methods for Word Sense Disambiguation (WSD). The method...
Abstract. We present a novel ensemble of six methods for improving the efficiency of chart realization. The methods are couched in the framework of Combinatory Categorial Grammar (...
Abstract. We present a new approach to the generation of referring expressions containing attributive, type and relational properties combined by conjunctions, disjunctions and neg...
Abstract. Discourse anaphora other than definite NPs have not received much attention in generation. This paper proposes a strategy for generating the additive particle also, a no...
Abstract. Although humans are the ultimate “natural language generators”, the area of psycholinguistic modeling has been somewhat underrepresented in recent approaches to Natur...
This paper describes an implemented model of context-based incremental tactical generation within the Dynamic Syntax framework [1] which directly reflects dialogue phenomena such ...