In the framework of a research target that aims at integration of sign language technologies to human-computer interaction applications, creation and annotation of the Greek Sign Language Corpus (GSLC) involve, on the one hand, data and analysis of the phonological structure of morphemes of Greek Sign Language (GSL) and, on the other hand, collection of sentence level language samples and assig...

In this paper, a new novelty detection approach based on the identification of sentence level information patterns is proposed. First, ‘‘novelty’’ is redefined based on the proposed information patterns, and several different types of information patterns are given corresponding to different types of users’ information needs. Second, a thorough analysis of sentence level information patterns is...

Popular products often have thousands of reviews that contain far too much information for customers to digest. Our goal for the project is to implement a system that extracts opinions from these reviews and summarizes them in a concise form. This allows customers to quickly get an overview of a product and manufactures to efficiently process product feedbacks. In the past, we focused on the fe...

We present an implementation of a discourse parsing system for a lexicalized TreeAjoining Grammar for discourse, specifying the integration of sentence and discourse level processing. Our system is based on the assumption that the compositional aspects of semantics at the discourse-level parallel those at the sentence-level. This coupling is achieved by factoring away inferential semantics and ...

In this paper we present the prototype based text matching methodology used in the Routing Sub-Task of TREC 2001 Filtering Track. The methodology examines texts on word and sentence levels. On the word level the methodology is based on word coding and transforming the codes into histograms by the means of Weibull distribution. On the sentence level the word coding is done in a similar manner as...

Constrained translation has improved statistical machine translation (SMT) by combining it with translation memory (TM) at sentence-level. In this paper, we propose using a constrained word lattice, which encodes input phrases and TM constraints together, to combine SMT and TM at phrase-level. Experiments on English– Chinese and English–French show that our approach is significantly better than...

Pathological speech usually refers to the condition of speech distortion resulting from atypicalities in voice and/or in the articulatory mechanisms owing to disease, illness or other physical or biological insult to the production system. Although automatic evaluation of speech intelligibility and quality could come in handy in these scenarios to assist experts in diagnosis and treatment desig...

0957-4174/$ see front matter 2012 Elsevier Ltd. A http://dx.doi.org/10.1016/j.eswa.2012.08.045 ⇑ Corresponding author. E-mail address: [email protected] (S.-J. L We present a novel method for detecting near-duplicates from a large collection of documents. Three major parts are involved in our method, feature selection, similarity measure, and discriminant derivation. To find near-dupli...

We address the question of whether and how boosting and bagging can be used for speech recognition. In order to do this, we compare two different boosting schemes, one at the phoneme level, and one at the utterance level, with a phoneme level bagging scheme. We control for many parameters and other choices, such as the state inference scheme used. In an unbiased experiment, we clearly show that...

In the present study we use the property of some linguistic items to express more than one meaning in order to investigate whether there is semantic priming at the sentence level. To test such a priming effect we use the connective because that can express a causal or purposive relation. If there is a priming effect, then participants will be expected to use causal because following causal prim...