1 |
Morphological Solutions for Arabic Statistical Machine Translation and Sentiment Analysis
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Morphological Solutions for Arabic Statistical Machine Translation and Sentiment Analysis
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Plasticity in the Human Speech Motor System Drives Changes in Speech Perception
|
|
|
|
In: ISSN: 0270-6474 ; EISSN: 1529-2401 ; Journal of Neuroscience ; https://hal.archives-ouvertes.fr/hal-01053445 ; Journal of Neuroscience, Society for Neuroscience, 2014, 34 (31), pp.10339-10346. ⟨10.1523/JNEUROSCI.0108-14.2014⟩ (2014)
|
|
BASE
|
|
Show details
|
|
4 |
READ THESE TERMS AND CONDITIONS CAREFULLY BEFORE USING THIS WEBSITE.
|
|
|
|
In: http://actr.psy.cmu.edu/papers/968/emond-winlex.pdf (2006)
|
|
BASE
|
|
Show details
|
|
5 |
Exploring Sentence Variations with Bilingual Corpora *
|
|
|
|
In: http://www.iit-iti.nrc-cnrc.gc.ca/iit-publications-iti/docs/NRC-48511.pdf (2005)
|
|
BASE
|
|
Show details
|
|
6 |
Software Support for Multi-Lingual Legislative Drafting
|
|
|
|
In: http://iit-iti.nrc-cnrc.gc.ca/iit-publications-iti/docs/NRC-48068.pdf (2004)
|
|
BASE
|
|
Show details
|
|
7 |
Real-Time Identification of Parallel Texts from Bilingual
|
|
|
|
In: http://iit-iti.nrc-cnrc.gc.ca/iit-publications-iti/docs/NRC-48081.pdf (2004)
|
|
BASE
|
|
Show details
|
|
8 |
Unsupervised Learning of Semantic Orientation from a Hundred-Billion-Word Corpus
|
|
|
|
In: http://extractor.iit.nrc.ca/publications/ERB-1094.pdf (2002)
|
|
Abstract:
The evaluative character of a word is called its semantic orientation. A positive semantic orientation implies desirability (e.g., "honest", "intrepid") and a negative semantic orientation implies undesirability (e.g., " disturbing", "superfluous"). This paper introduces a simple algorithm for unsupervised learning of semantic orientation from extremely large corpora. The method involves issuing queries to a Web search engine and using pointwise mutual information to analyse the results. The algorithm is empirically evaluated using a training corpus of approximately one hundred billion words --- the subset of the Web that is indexed by the chosen search engine. Tested with 3,596 words (1,614 positive and 1,982 negative), the algorithm attains an accuracy of 80%. The 3,596 test words include adjectives, adverbs, nouns, and verbs. The accuracy is comparable with the results achieved by Hatzivassiloglou and McKeown (1997), using a complex four-stage supervised learning algorithm that is restricted to determining the semantic orientation of adjectives.
|
|
Keyword:
1. Semantic Orientation from Association.
|
|
URL: http://extractor.iit.nrc.ca/publications/ERB-1094.pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.8133
|
|
BASE
|
|
Hide details
|
|
|
|