Semantic clusters of a domain form an important feature that can be useful for performing syntactic and semantic disambiguation. Several attempts have been made to extract the semantic clusters of a domain by probabilistic or taxonomic techniques. However, not much progress has been made in evaluating the obtained semantic clusters. This paper focuses on an evaluation mechanism that can be used...

This paper presents an empirical analysis of prosodic phenomena (intonation and timing) in 'common ground units' (Nakatani & Traurn 1999). The analysis is used to address questions of the role of prosody in dialogue while taking into account the complexities of multispeaker discourse. We address some methodological concerns of how best to carry out a study of this kind as well as our theoretica...

This paper deals with the semantic representation of user utterances within development of computerized dialogue system intended for city information center. The formalisms for description of natural language are mentioned and verified on user utterances and first dialogue turns within selected domain areas. A parser analyzing the utterance segments according to given rules is presented. Then t...

In this paper we present a novel method for semantic entity detection in a limited domain for spoken language understanding. The target domain of this method is a dialogue system for an interactive training of air traffic controllers (ATC). Themethod comprises of two layers of detection. First layer uses formerly proposed method for semantic entity detection to extract domain-dependent set of s...

Both similarity-based and popularity-based document ranking functions have been successfully applied to information retrieval (IR) in general. However, the dimension of semantic granularity also should be considered for effective retrieval. In this paper, we propose a semantic granularity based IR model which takes into account the three dimensions, namely similarity, popularity, and semantic g...

Sentiment analysis of weblogs is a challenging problem. Most previous work utilized semantic orientations of words or phrases to classify sentiments of weblogs. The problem with this approach is that semantic orientations of words or phrases are investigated without considering the domain of weblogs. Weblogs contain the author’s various opinions about multifaceted topics. Therefore, we have to ...

Semantic technologies which visualise complete ontologies in network form are manifold; yet such semantic networks remain for the most part exclusively within the grasp of domain experts. In this paper, we suggest that semantic networks representing foreign domains can indeed present many benefits to the common enduser, as long as certain semantic objects from the domain are extracted and only ...

Style transfer usually refers to the task of applying color and texture information from a specific style image to a given content image while preserving the structure of the latter. Here we tackle the more generic problem of semantic style transfer: given two unpaired collections of images, we aim to learn a mapping between the corpus-level style of each collection, while preserving semantic c...