History of natural language processing: Difference between revisions

Revision as of 05:30, 15 November 2012

Revision as of 09:44, 8 February 2013

Line 7:

The first patents for "translating machines" were applied for in the mid 1930s. One proposal, by [[Georges Artsrouni]] was simply an automatic bilingual dictionary using [[paper tape]]. The other proposal, by [[Peter Troyanskii]], a [[Russians|Russian]], was more detailed. It included both the bilingual dictionary, and a method for dealing with grammatical roles between languages, based on [[Esperanto]].

In 1950, [[Alan Turing]] published his famous article "[[Computing Machinery and Intelligence]]"<ref>{{Harv|Turing|1950}}</ref> which proposed what is now called the [[Turing test]] as a criterion of intelligence. This criterion depends on the ability of a computer program to impersonate a human in a real-time written conversation with a human judge, sufficiently well that the judge is unable to distinguish reliably -&nbsp;— on the basis of the conversational content alone -&nbsp;— between the program and a real human.

In 1957, [[Noam Chomsky]]’s [[Syntactic Structures]] revolutionized Linguistics with '[[universal grammar]]', a rule based system of syntactic structures.<ref>{{cite web

Line 15:

}}</ref>

However,The the[[Georgetown-IBM realexperiment|Georgetown progressexperiment]] in 1954 involved fully automatic translation of NLPmore than sixty Russian sentences into English. The authors claimed that within three or five years, machine translation would be a solved problem.<ref>Hutchins, J. (2005)</ref> However, real progress was much slower, and after the [[ALPAC|ALPAC report]] in 1966, which found that ten years long research had failed to fulfill the expectations, funding for machine translation was dramatically reduced internationally. Little further research in machine translation was conducted until the late 1980s, when the first [[statistical machine translation]] systems were developed.

Some notably successful NLP systems developed in the 1960s were [[SHRDLU]], a natural language system working in restricted "[[blocks world]]s" with restricted vocabularies, and [[ELIZA]], a simulation of a [[Rogerian psychotherapy|Rogerian psychotherapist]], written by [[Joseph Weizenbaum]] between 1964 to 1966. Using almost no information about human thought or emotion, ELIZA sometimes provided a startlingly human-like interaction. When the "patient" exceeded the very small knowledge base, ELIZA might provide a generic response, for example, responding to "My head hurts" with "Why do you say your head hurts?".

In 1969 [[Roger Schank]] introduced the [[conceptual dependency theory]] for natural language understanding.<ref>[[Roger Schank]], 1969, ''A conceptual dependency parser for natural language'' Proceedings of the 1969 conference on Computational linguistics, Sång-Säby, Sweden, pages 1-3</ref> This model, partially influenced by the work of [[Sydney Lamb]], was extensively used by Schank's students at [[Yale University]], such as Robert Wilensky, Wendy Lehnert, and [[Janet Kolodner]].

In 1970, William A. Woods introduced the [[augmented transition network]] (ATN) to represent natural language input.<ref>Woods, William A (1970). "Transition Network Grammars for Natural Language Analysis". Communications of the ACM 13 (10): 591–606 [http://www.eric.ed.gov/ERICWebPortal/custom/portlets/recordDetails/detailmini.jsp?_nfpb=true&_&ERICExtSearch_SearchValue_0=ED037733&ERICExtSearch_SearchType_0=no&accno=ED037733]</ref> Instead of ''[[phrase structure rules]]'' ATNs used an equivalent set of [[finite state automata]] that were called recursively. ATNs and their more general format called "generalized ATNs" continued to be used for a number of years.During the 70's many programmers began to write 'conceptual ontologies', which structured real-world information into computer-understandable data. Examples are MARGIE (Schank, 1975), SAM (Cullingford, 1978), PAM (Wilensky, 1978), TaleSpin (Meehan, 1976), QUALM (Lehnert, 1977), Politics (Carbonell, 1979), and Plot Units (Lehnert 1981). During this time, many [[chatterbots]] were written including [[PARRY]], [[Racter]], and [[Jabberwacky]].

Up to the 1980s, most NLP systems were based on complex sets of hand-written rules. Starting in the late 1980s, however, there was a revolution in NLP with the introduction of [[machine learning]] algorithms for language processing. This was due both to the steady increase in computational power resulting from [[Moore's Law]] and the gradual lessening of the dominance of [[Noam Chomsky|Chomskyan]] theories of linguistics (e.g. [[transformational grammar]]), whose theoretical underpinnings discouraged the sort of [[corpus linguistics]] that underlies the machine-learning approach to language processing.<ref>Chomskyan linguistics encourages the investigation of "[[corner case]]s" that stress the limits of its theoretical models (comparable to [[pathological (mathematics)|pathological]] phenomena in mathematics), typically created using [[thought experiment]]s, rather than the systematic investigation of typical phenomena that occur in real-world data, as is the case in [[corpus linguistics]]. The creation and use of such [[text corpus|corpora]] of real-world data is a fundamental part of machine-learning algorithms for NLP. In addition, theoretical underpinnings of Chomskyan linguistics such as the so-called "[[poverty of the stimulus]]" argument entail that general learning algorithms, as are typically used in machine learning, cannot be successful in language processing. As a result, the Chomskyan paradigm discouraged the application of such models to language processing.</ref> Some of the earliest-used machine learning algorithms, such as [[decision tree]]s, produced systems of hard if-then rules similar to existing hand-written rules. Increasingly, however, research has focused on [[statistical natural language processing|statistical models]], which make soft, [[probabilistic]] decisions based on attaching [[real-valued]] weights to the features making up the input data. The [[cache language model]]s upon which many [[speech recognition]] systems now rely are examples of such statistical models. Such models are generally more robust when given unfamiliar input, especially input that contains errors (as is very common for real-world data), and produce more reliable results when integrated into a larger system comprising multiple subtasks.

Many of the notable early successes occurred in the field of [[machine translation]], due especially to work at IBM Research, where successively more complicated statistical models were developed. These systems were able to take advantage of existing multilingual [[text corpus|textual corpora]] that had been produced by the [[Parliament of Canada]] and the [[European Union]] as a result of laws calling for the translation of all governmental proceedings into all official languages of the corresponding systems of government. However, most other systems depended on corpora specifically developed for the tasks implemented by these systems, which was (and often continues to be) a major limitation in the success of these systems. As a result, a great deal of research has gone into methods of more effectively learning from limited amounts of data.

Recent research has increasingly focused on [[unsupervised learning|unsupervised]] and [[semi-supervised learning|semi-supervised]] learning algorithms. Such algorithms are able to learn from data that has not been hand-annotated with the desired answers, or using a combination of annotated and non-annotated data. Generally, this task is much more difficult than [[supervised learning]], and typically produces less accurate results for a given amount of input data. However, there is an enormous amount of non-annotated data available (including, among other things, the entire content of the [[World Wide Web]]), which can often make up for the inferior results.

==Software==