1. rc. word ng. recurring word-based n-grams 2. rc. OCPOS ng. recurring n-grams, where open class words are replaced by POS tags 3. rc. word dep. rec. word-based dependencies (MATE): a head and all its immediate dependents, ordered as in the sentence Ex: My own experience confirms this fact. ⇒ (my, own, experience); (experience, confirms, fact); (this, fact) 4. rc. func. dep. rec. function-base...

We describe a multi-stage speech production model containing a linear, phoneme-independent coarticulation lter, followed by a nonlinear component. The latter generates two cepstra which are then additively combined: one corresponding to a relatively smooth background spectrum, and the other representing three formant-like spectral peaks. A neural net is used for both parts, but the second part ...

<>=@?BA CED F G#FIH J7KLH FMJBHND HN=+?OG5P'Q D CER;GTS*DU?8V SEH)CXW HN=+?BCEY R;GT?BCEZ#='D R(A HNP-H

The automatic grading of oral language tests has been the subject of much research in recent years. Several obstacles lie in the way of achieving this goal. Recent work suggests a testing technique called elicited imitation (EI) that can serve to accurately approximate global oral proficiency. This testing methodology, however, does not incorporate some fundamental aspects of language, such as ...

The notion of exploiting data dependent hypothesis spaces is an exciting new direction in machine learning with strong theoretical foundations[66]. A very practical motivation for these techniques is that they allow us to exploit unlabeled data in new ways [2]. In this work we investigate a particular technique for combining “native” features with features derived from a similarity function. We...

In automated face recognition, a human face can be described by several features, but very few of them are used in combination to improve discrimination ability. This paper demonstrates how different feature sets can be used to enhance discrimination for the purpose of face recognition. We have used geometrical features and Gabor features in combination for face recognition. The geometrical fea...

Authorship analysis is an important task for different text applications, for example in the field of digital forensic text analysis. Hence, we propose an authorship analysis method that compares the average similarity of a text of unknown authorship with all the texts of an author. Using this idea, a text that was not written by an author, would not exceed the average of similarity with known ...

Object recognition algorithms usually identify: 1) pointbased features and 2) global structure/geometric shape of an object to solve the recognition problem. In this paper, we propose a framework that integrates these two approaches and brings forth the advantages of both to achieve higher recognition rates. In our framework, the object features are represented using biologically motivated C2 d...

Neural network models have recently received heated research attention in the natural language processing community. Compared with traditional models with discrete features, neural models have two main advantages. First, they take low-dimensional, real-valued embedding vectors as inputs, which can be trained over large raw data, thereby addressing the issue of feature sparsity in discrete model...

We aim at combining color and shape invariants for indexing and retrieving images. To this end, color models are proposed independent of the object geometry, object pose, and illumination. From these color models, color invariant edges are derived from which shape invariant features are computed. Computational methods are described to combine the color and shape invariants into a unified high-d...