HUMAN LANGUAGE TECHNOLOGIES

Human language techonology or HLT, it’s not only composed of computational linguistics, but also of speech technology. It’s important also to bear in mind, that Human Language Technology or Language technology is connected to both, computer science and general linguistics.

According to Hans Uszkoreit : “human language technology comprises computational methods, computer programs and electronic devices that are specialized for analyzing, producing or modifying texts and speech.” Apart from that, he also points out that we have to take into account that: “these systems must be based on some knowledge of human language. Therefore language technology defines the engineering branch of computational linguistics.” (gehiago…)

Advertisements

2009/06/18 at 6:27 pm Utzi iruzkina

Kaiola ertzetik begiratzen dut

Gustoko nuen bizi hura, gustoko nuen benetan aire garbian bidaiatzen genueneko garai haiek, gogoko nituen benetan kezkarik gabeko une haiek eta biziki gogoko nituen bai, aske eta libre nintzeneko momentu zoragarri zein liluragarri haiek.

Ni beti izan naiz izaera lasai eta trankilekoa, orain berriz egunak joan egunak etorri, nire lasaitasun haren tokia etorri berri den urduritasunezko sentimendu batek bereganatu du; lehoiak, bere presa, bere atzamar handi eta indartsuen bitartez harrapatzen duen moduan. Horrela jokatu du demoniozko urduritasun honek ere; gupidarik gabe alegia. Baina bisita egitera etorri zitzaidan etsai bakarra ez da urduritasun desatsegin hau izan, ez jauna! Urduritasuna etorri eta hurrengo egunean, tristura etorri zen bihotz joka. Bisitari honek ezustean harrapatu ninduen eta arrapaladan sartu zen barrura, prisa izango balu bezala. Joateko aldiz, ez zuen inolako prisarik izango, alderantziz baizik; gustura sentitzen zela eta nirekin geldituko zen luzaroan, betirako ez esateagatik. Baina, ez da hau guztia, beste hainbat bisitari ere izan bainituen, denak nirekin gelditzeko nolabaiteko esperantza zutelarik: atsekabea, estresa, goibeltasuna, mina, depresioa, ahuldura eta azkenik heriotza. (gehiago…)

2009/06/17 at 6:33 pm Utzi iruzkina

QUESTION ANSWERING SYSTEMS (Questionnaire 3)

On the web we could find answers to a huge range of questions. This is possible because of the extraordinary quantity of information which is obtainable online.

Question answering, well known as QA, is the assignment of answering a question which is presented in natural language. The QA computer have to answer to the posed question; for that matter, the QA computer program will use a pre-structured database or a collection of natural language documents. Both options are possible.

Question answering research makes a shot at dealing with an ample coverage of question types including fact, list, definition, how, why, hypothetical, semantically-constrained, and cross-lingual questions. (gehiago…)

2009/06/16 at 7:47 pm Utzi iruzkina

Machine Translation (Questionnaire 3)

Machine Translation is the utilization of computers to the assignment of translating a text from a natural language, to another one. MT is one of the earliest researches in computer science. It has demonstrated to be a fleeting goal. Nowadays there are many systems which produce results with enough quality to be useful in so many specific fields.

At its simple grade, Machine translation makes simple exchanges of words in a natural language for word in another. Otherwise, with corpus techniques, the translation will be more complex.

Definition from the European Association for Machine Translation: “an organization that serves the growing community of people interested in MT and translation tools, including users, developers, and researchers of this increasingly viable technology”. (gehiago…)

2009/05/02 at 12:37 pm Iruzkin 1

Word-Sense Disambiguation (Questionnaire 2)

Word sense disambiguation (well known as WSD) have place in software programs which are designed to interpret the language. There are many ambiguous words and sentences which have more than one sense and can be understood in many different ways although only one sense in pretended. The main goal of disambiguation is to figure out the pretended or intended meaning.

This is a clear example of a written word which has two distinct senses or meanings:

For example, the written word “bass” has those two senses:

  1. bass = a kind of fish
  2. bass = tones of low frequency (gehiago…)

2009/04/28 at 7:59 pm Utzi iruzkina

Automatic Summarization (Questionnaire 2)

Automatic summarization is the formation of an abbreviated version of a text, made by a computer program. The main objective of automatic summarization is the following:  first, to take a source of information. After that,  to draw out the contained substance from it and finally, to present the major content to the user in a summarized way. And of course,  in a sensitive way taking into account the users’ needs.

Because of the phenomenon of information overload, we know that the access to  solid and properly-developed summaries is essential. One of the examples we have of the use of summarization technology, is a search engine called Google.

Those technologies have to bear in mind the length, the writing-style and the syntax, in order to make a useful summary of any type of text. (gehiago…)

2009/04/25 at 11:08 pm Utzi iruzkina

Information Extraction (Questionnaire 2)

As Jim Cowie and Yorick Wilks say, this name (Information Extraction) is given to a process that discriminatively structures and also combines data found in only one, or more texts. The ending outcome of the process of extraction changes; nevertheless, it can be transformed in order to populate some database type. Information analyst who have worked long run on particular assignment have already carried out information extraction manually with the main of database creation.

The importance of Information Extraction is determined by the huge amount of information available in a badly built form; internet is a good example of this fact. Those unstructured information can be made more accessible by transforming into relational form or also by marking-up with XML tags. To transform unstructured data into something that can be reasoned with, is required Information Extraction. (gehiago…)

2009/03/28 at 5:51 pm Utzi iruzkina

Post zaharragoak Posta Berrienak


Azken postak

Artxiboak

2017(e)ko Iraila
A A A A O I I
« Urt    
 123
45678910
11121314151617
18192021222324
252627282930  

Feeds

RSS amaiaren bloga

RSS CiteUlike

RSS Google Books

  • An error has occurred; the feed is probably down. Try again later.