<span style="color: #000000; font-family: Tahoma, sans-serif; font-size: 13px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: -webkit-left; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; display: inline !important; float: none; ba...

Named entity recognition is a fundamental task in biomedical data mining. Multiple -class annotation is more challenging than single class annotation. In this paper, we took a single word classification approach to dealing with the multiple -class annotation problem using Support Vector Machines (SVMs). Word attributes, results of existing gene/protein name taggers, context, and other informati...

Previous research on word class distribution claimed that 37% of word tokens are nouns, suggesting that there might exist a certain regularity of noun proportion 15 among human languages. To explore this possibility, we examined the proportion of noun and four other word classes within British and American English, and across seven languages in terms of different word frequency band. Results in...

The aim of this paper is to report on an attempt to design and implement an intelligent system capable of generating the correct part of speech for a given sentence while the sentence is totally new to the system and not stored in any database available to the system. It follows the same steps a normal individual does to provide the correct parts of speech using a natural language processor. It...

This paper presents electrophysiological evidence of an impairment in the on-line processing of word class information in patients with Broca's aphasia with agrammatic comprehension. Event-related brain potentials (ERPs) were recorded from the scalp while Broca patients and non-aphasic control subjects read open- and closed-class words that appeared one at a time on a PC screen. Separate wavefo...

We investigate different types of features for language modeling in Arabic automatic speech recognition. While much effort in language modeling research has been directed at designing better models or smoothing techniques for n-gram language models, in this paper we take the approach of augmenting the context in the n-gram model with different sources of information. We start by adding word cla...

This paper proposes an unsupervised, batch-type, class-based language model adaptation method for spontaneous speech recognition. The word classes are automatically determined by maximizing the average mutual information between the classes using a training set. A class-based language model is built based on recognition hypotheses obtained using a general word-based language model, and linearly...

There are various applications where homotopy constraints are useful in trajectory generation for mobile robots. In this paper, we present a method to generate an optimal trajectory restricted to a particular homotopy class, which is specified by a given representative trajectory. The optimality is achieved by formulating the trajectory generation problem as a Mixed-Integer Quadratic Program (M...

This paper proposes an unsupervised, batch-type, class-based language model adaptation method for spontaneous speech recognition. The word classes are automatically determined by maximizing the average mutual information between the classes using a training set. A class-based language model is built based on recognition hypotheses obtained using a general word-based language model, and linearly...

This paper describes our research on statistical language modeling of Lithuanian. The idea of improving sparse n-gram models of highly inflected Lithuanian language by interpolating them with complex n-gram models based on word clustering and morphological word decomposition was investigated. Words, word base forms and part-of-speech tags were clustered into 50 to 5000 automatically generated c...