|
|
|
|
|
|
Date Reviewed |
|
|
1 - 10 of 22
reviews
|
|
|
|
|
|
|
|
Accessor variety criteria for Chinese word extraction Feng H., Chen K., Deng X., Zheng W. Computational Linguistics 30(1): 75-93, 2004. Type: Article
The extraction of unknown words--such as compound nouns, and the names of people and organizations--is crucial for success in broad areas of language processing in Chinese, including machine translation and informatio...
|
Jan 7 2005 |
|
|
|
|
|
|
Automating survey coding by multiclass text categorization techniques Giorgetti D., Sebastiani F. Journal of the American Society for Information Science and Technology 54(14): 1269-1277, 2003. Type: Article
In some kinds of surveys and questionnaires, questions allow open-ended, free-text responses, which must then be placed into categories by coders. For example, a question on the causes of a subject’s anger might require the a...
|
Mar 1 2004 |
|
|
|
|
|
|
Visual unrolling of network evolution and the analysis of dynamic discourse Brandes U., Corman S. Information Visualization 2(1): 40-50, 2003. Type: Article
Brandes and Corman describe a method of visualizing a series of changes in a graph (an evolving network) as a stack of layers, one for each time step. Each vertex is thus a column at a fixed point through the layers in which it persist...
|
Dec 30 2003 |
|
|
|
|
|
|
Mining text documents for thematic hierarchies using self-organizing maps Yang H., Lee C. In Data mining. Hershey, PA: Idea Group Publishing, 2003. Type: Book Chapter
The automatic classification of documents is a hot topic in natural language processing research right now, and consequently, so is the automatic generation of document classification schemes. Hierarchical classifications, rather than ...
|
Oct 21 2003 |
|
|
|
|
|
|
Exploiting syntactic analysis of queries for information retrieval Mittendorfer M., Winiwarter W. Data & Knowledge Engineering 42(3): 315-325, 2002. Type: Article
It is often thought that information retrieval would be improved by performing full linguistic analyses on queries and documents, rather than just treating them as strings or bags of words. After all, if the system fully “un...
|
Mar 11 2003 |
|
|
|
|
|
|
Meaningful term extraction and discriminative term selection in text categorization via unknown-word methodology Lai Y., Wu C. ACM Transactions on Asian Language Information Processing 1(1): 2002. Type: Article
Text categorization is the process of assigning documents to pre-defined categories. For example, news articles could be categorized as sports, finance, and so on. Conventional methods of text categorization use a set of pre-classifie...
|
Aug 5 2002 |
|
|
|
|
|
|
Taming recognition errors with a multimodal interface Oviatt S. Communications of the ACM 43(9): 45-51, 2000. Type: Article
Contemporary speech recognition systems are still prone to much error, especially when dealing with difficult conditions, such as the background noise of public places or the accents of nonnative speakers. Analogous problems occur with...
|
Oct 1 2000 |
|
|
|
|
|
|
Computer and natural language texts--a comparison based on long-range correlations Kokol P., Podgorelec V., Zorman M., Kokol T., Njivar T. Journal of the American Society for Information Science 50(14): 1295-1301, 1999. Type: Article
The amount of uncertainty in a signal is usually measured by its entropy, as first defined by Shannon. The entropy of natural languages such as English is not known, though a number of experiments [1,2] have attempted to estimate it. A...
|
Feb 1 2000 |
|
|
|
|
|
|
The Unicode standard, version 2.0 , Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1996. Type: Book (9780201483451)
Unicode is a 16-bit encoding scheme for written characters, intended to cover all the major alphabetic and ideographic writing systems of the world. The encoding has been developed by the Unicode Consortium, whose members include most ...
|
Oct 1 1997 |
|
|
|
|
|
|
The EDR electronic dictionary Yokoi T. Communications of the ACM 38(11): 42-44, 1995. Type: Article
Serious linguistic applications, such as machine translation and knowledge acquisition from text, require systems that have considerable knowledge about the words of the natural language or languages involved and the relationship betwe...
|
Dec 1 1996 |
|
|
|
|
|
|
|
|
|
|
|