We propose a new computational method to support learning that relies on adaptive exploration of the shortest paths in conceptual networks that have been formed based on cooccurrences of concepts in suitable text samples and selecting concepts corresponding to desired language ability levels and frequency ranking. Relying on Google Web 1T 5-gram database we have built a conceptual co-occurrence...

convictions are strong that multimedia courseware holds great promise for enhancing learning efficiency among learners. this study thus aimed at comparing the effects of the multimedia programs introducing 100 vocabulary items through pictures and streaming video with those of teacher instruction on increasing efl learners’ vocabulary repertoire. a total of 120 subjects were identified as inter...

Common approaches to assessing document quality look at shallow aspects, such as grammar and vocabulary. For many real-world applications, deeper notions of quality are needed. This work represents a first step in a project aimed at developing computational methods for deep assessment of quality in the domain of intelligence reports. We present an automated system for ranking intelligence repor...

An experimental speech recognition system was developed for German using an already existing technology reported elsewhere (1). The system recognizes complete sentences when the words are spoken with a small pause in between. The user has to train the system in advance by uttering 110 short sentences. The size of the system's vocabulary is presently limited to about 1300 words, with a coverage ...

AI applications often receive their input in the form of natural language text, or as the transcription of spoken text. A commonsense inference system should transform such input to a formal representation with limited vocabulary in order to be able to process them. In this paper, we present a method based on neural word embeddings that automatically assigns semic features to words of natural l...

This work presents the general idea of granular description of temporal signal, particularly biomedical signal sampled with constant frequency. The main idea of presented method is based on using triangular fuzzy numbers as information granules in temporal and amplitude spaces. The amplitude space contains values of first few derivatives of underlying signal. The construction of data granules i...

Word embeddings – distributed representations of words – in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured semantics. Instead of relying on a more advanced algorithm for embedding learning, this paper proposes an ensemble approach of combining different public embeddi...

In this paper we show an approach to the customization of GermaNet to the German HPSG grammar lexicon developed in the Verbmobil project. GermaNet has a broad coverage of the German base vocabulary and fine grained semantic classification, while the HPSG grammar lexicon is comparatively small und has a coarse-grained semantic classification. In our approach, we have developed a mapping algorith...

This paper describes baseNP supersense tagging for Japanese texts. The task extracts base noun phrases (baseNPs) from raw texts in Japanese, and labels their baseNPs with supersenses. This task has a number of applications including predicate argument structure analysis and question answering. While the definition of baseNP in English is relatively clear, its definition in Japanese has not yet ...