[PDF][PDF] Word representations: a simple and general method for semi-supervised learning
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 …
accuracy is to use unsupervised word representations as extra word features. We evaluate …
Revealing dimensions of thinking in open-ended self-descriptions: An automated meaning extraction method for natural language
CK Chung, JW Pennebaker - Journal of research in personality, 2008 - Elsevier
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 …
1165 open-ended self-descriptive narratives. Drawing on a lexical approach to personality …
Meaning and the brain: The neurosemantics of referential, interactive, and combinatorial knowledge
F Pulvermüller - Journal of Neurolinguistics, 2012 - Elsevier
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 …
and words? Philosophers were the first to point out that the arbitrary links between signs and …
Learning representations for weakly supervised natural language processing tasks
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 …
domain-specific labeled data for the task is scarce. This article investigates novel techniques …
[图书][B] Induction of the morphology of natural language: Unsupervised morpheme segmentation with application to automatic speech recognition
M Creutz - 2006 - aaltodoc.aalto.fi
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 …
(text and speech), one needs good models of the vocabulary and grammar of as many …
Independent components of word embeddings represent semantic features
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 …
separate sources in a mixed signal, such as a recording of multiple people in the same room …
WordICA—emergence of linguistic representations for words by independent component analysis
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 …
linguistic roles or features of words. The extraction is based on the unsupervised analysis of …
Learning Phonological Categories by Independent Component Analysis∗
B Calderone - Journal of Quantitative Linguistics, 2009 - Taylor & Francis
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 …
basis of their distributional information within a representative corpus. We focus on some …
Sparse distributed representations for words with thresholded independent component analysis
JJ Vayrynen, L Lindqvist… - 2007 International Joint …, 2007 - ieeexplore.ieee.org
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 …
representations for words that can be further processed by thresholding to produce sparse …
[图书][B] Exploiting knowledge in NLP
L Ratinov - 2012 - search.proquest.com
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 …
tasks. The first steps in NLP applications involve identification of topics, entities, concepts …