Since Cilenis esmerándonos continue to make the portal Linguakit preferred by expert linguists, journalists, editors, publishers, teachers, students, or any user of the language. So today Linguakit integrates two more linguistic tools: the extractor program and extractor keywords multipalabra, a tool unique and rare in this field. With them you can get the most relevant information from a written text.
By introducing a text extractor keywords or extractor multipalabra of Linguakitobterás automatically the words or group of words highlights, sorted program in descending order according to their degree of relevance. Furthermore, these words are highlighted in the text itself, program complementing the extraction with a view of the terms.
To perform this classification, the extractor keywords based on a model of observed frequencies and frequencies estimated. Thus, the system calculates the weight of the words in the text, using statistical test carried out with a comparison between the observed frequency of the words of the text with the estimated frequency, that is, as often as they should have those words in the corpus or corpus ideal reference.
In the case of the extractor multipalabra, the strategy is different. Integrates program two processes in which, first, identifies the "candidates" to multipalabra terms, which must belong to a standard grammar program name-name-preposition, adjective-name, name-adjective; and secondly, ordered from highest to lowest relevance following statistical measures of association.
Also, another difference between both extractors is the output program of information that the system provides you. By introducing a text extractor keywords first you will return the system is a cloud built with the most important words of the text, highlighted in different colors and sizes according to their degree of relevance. You choose the number of words that appear in this cloud.
These two linguistic tools are very useful for the detection of a subject quickly and automatically, which greatly facilitates the classification and labeling documentary. Even if you need to expand the search keywords to terms and topics that need more than one word to express, you can do the extractor multipalabra. Therefore, the combination of these two instruments the result program is much more powerful.
Recent articles Linguakit changes program appearance with Fixes Linguakit The translator expands suite of tools Linguakit Linguakit determines the frequency of the words Galician Android keyboard made in Galicia
Tweets RTrainhavermella: Promoting #tecladogalego ofcilenis_com between the Galician literary criticism! July 31, 2014 - 7:07 PM RTrainhavermella: I already have #tecladogalego ofcilenis_com! July 30, 2014 - 9:38 PM RTjmgomez: MTLinguaKitcitiusus /imaxinsoftware team Leaded bypgamalhoCILENIS 1st unconstrained competition in TweetLID http: // t ... July 29, 2014 - 9:19 AM
We use cookies themselves and others to improve our website by analyzing your browsing on our website. If you continue to browse, consider that you agree to its use. Accept
No comments:
Post a Comment