Natural Language Processing: A Historical Review*
نویسنده
چکیده
This paper reviews natural language processing (NLP) from the late 1940's to the present, seeking to identify its successive trends as these reflect concerns with different problems or the pursuit of different approaches to solving these problems and building systems as wholes. The review distinguishes four phases in the history of NLP, characterised respectively by an emphasis on machine translation, by the influence of artificial intelligence, by the adoption of a logico-grammatical style, and by an attack on massive language data. The account considers the significant and salient work in each phase, and concludes with an assessment of where we stand after more than forty years of effort in the field.
منابع مشابه
A Survey of Natural Language Processing and Machine Translation in Japan
In this survey brief historical review of natural language processing and machine translation in Japan is given first. This is followed by an explanation of a few typical research results in the morphological and syntactic analyses of the Japanese language. Machine translation has been getting the spotlight once again in Japan. Two research results are explained in some detail. One is the machi...
متن کاملComparing Canonicalizations of Historical German Text
Historical text presents numerous challenges for contemporary natural language processing techniques. In particular, the absence of consistent orthographic conventions in historical text presents difficulties for any system requiring reference to a static lexicon accessed by orthographic form. In this paper, we present three methods for associating unknown historical word forms with synchronica...
متن کاملA Finite-State Approach to the Computational Morphology of Early Modern Greek
We present a finite-state approach to the computational morphology of early Modern Greek that improves the efficiency of searching and accessing to the “Politimo” corpus, which consists of Greek documents printed during the 17th and 18th centuries. Computational morphologies provide users the ability to search documents using only a word root and locate all the corresponding inflected words. Ke...
متن کاملLearning for Semantic Interpretation: Scaling Up without Dumbing Down
Most recent research in learning approaches to natural language have studied fairly \low-level" tasks such as morphology, part-ofspeech tagging, and syntactic parsing. However, I believe that logical approaches may have the most relevance and impact at the level of semantic interpretation, where a logical representation of sentence meaning is important and useful. We have explored the use of in...
متن کاملConstructing a Canonicalized Corpus of Historical German by Text Alignment ---draft
Historical text presents numerous challenges for contemporary natural language processing techniques. In particular, the absence of consistent orthographic conventions in historical text presents difficulties for any system requiring reference to a static lexicon indexed by orthographic form. Canonicalization approaches seek to address these issues by assigning an extant equivalent to each word...
متن کامل