Background: Variability in speech performance is a major concern for children with cochlear implants (CIs). Spectral resolution is an important acoustic component in speech perception. Considerable variability and limitations of spectral resolution in children with CIs may lead to individual differences in speech performance. The aim of this study was to assess the correlation between auditory ...

While other word-level marking tasks such as morphology and part-of-speech tagging have arrived recently at a well-developed methodology and a basis for comparing results across systems, the robust discrimination of word senses in text is a less mature discipline. Yet, word sense discrimination is central to many natural language processing tasks, such as data extraction and machine translation.

This paper presents a method of unsupervised word sense discrimination that augments co–occurrence feature vectors derived from raw untagged corpora with information from the glosses found in a machine readable dictionary. Each content word that occurs in the context of a target word to be discriminated is represented by a co-occurrence feature vector. Each of these vectors is augmented with th...

Task-specific word identification aims to choose the task-related words that best describe a short text. Existing approaches require well-defined seed words or lexical dictionaries (e.g., WordNet), which are often unavailable for many applications such as social discrimination detection and fake review detection. However, we often have a set of labeled short texts where each short text has a ta...

This study examined two possible sources of individual differences in crosslanguage speech perception, the capacity to phonologically encode speech and short-term memory span. Phonological coding was defined as the ability to encode non-native contrasts as distinct phonemes based on representations in long-term memory. Short-term memory was defined as a fixed capacity regulating the extent of e...

One of the attractions of neural network approaches to pattern recognition is the use of a discrimination-based training method. We show that once we have modified the output layer of a multilayer perceptron to provide mathematically correct probability distributions, and replaced the usual squared error criterion with a probability-based score, the result is equivalent to Maximum Mutual Inform...