If we take an existing supervised NLP system, a simple and general way to improve
accuracy is to use unsupervised word representations as extra word features. We evaluate …

A new method for extracting common themes from written text is introduced and applied to
1165 open-ended self-descriptive narratives. Drawing on a lexical approach to personality …

Which types of nerve cell circuits enable humans to use and understand meaningful signs
and words? Philosophers were the first to point out that the arbitrary links between signs and …

Finding the right representations for words is critical for building accurate NLP systems when
domain-specific labeled data for the task is scarce. This article investigates novel techniques …

In order to develop computer applications that successfully process natural language data
(text and speech), one needs good models of the vocabulary and grammar of as many …

Independent Component Analysis (ICA) is an algorithm originally developed for finding
separate sources in a mixed signal, such as a recording of multiple people in the same room …

We explore the use of independent component analysis (ICA) for the automatic extraction of
linguistic roles or features of words. The extraction is based on the unsupervised analysis of …

This work aims at discovering, in an unsupervised fashion, the nature of phonemes on the
basis of their distributional information within a representative corpus. We focus on some …

We show that independent component analysis (ICA) can be used to find distributed
representations for words that can be further processed by thresholding to produce sparse …

In recent decades, the society depends more and more on computers for a large number of
tasks. The first steps in NLP applications involve identification of topics, entities, concepts …