Microsoft Natural Language Understanding System and Grammar Checker
نویسنده
چکیده
The Natural Language Processing (NLP) group at Microsoft Research has been working for over five years on the development of a broad-coverage NL understanding system. In the last two years, the NLP group has been joined by the World Languages Research group, whose current mission is to extend the NLP group's technology to both European and Far-Eastern languages, and by the Natural Language Development group, which is responsible for transferring the technology into Microsoft products.
منابع مشابه
Some problems related to the development of a grammar checker
Developing a grammar checker presents problems to the linguist and to linguistic software that are far from trivial. In this paper we will discuss various kinds of problems that we have encountered during our work with developing a grammar checker for Norwegian (Bokmål). The grammar checker in question, developed in cooperation with Lingsoft OY and to be used in Microsoft Word from the summer 2...
متن کاملA rule-based Afan Oromo Grammar Checker
Natural language processing (NLP) is a subfield of computer science, with strong connections to artificial intelligence. One area of NLP is concerned with creating proofing systems, such as grammar checker. Grammar checker determines the syntactical correctness of a sentence which is mostly used in word processors and compilers. For languages, such as Afan Oromo, advanced tools have been lackin...
متن کاملEvaluating Two Web-based Grammar Checkers-Microsoft ESL Assistant and NTNU Statistical Grammar Checker
Many ESL students need to improve writing skills to pass various language tests; thus, writing teachers need to read many compositions and provide feedback. To help ESL teachers reduce their teaching load and to give students faster feedback, various English grammar checkers have been developed. Few of these PC-based grammar checkers, however, are widely available to ESL learners. As the Intern...
متن کاملImproving CoGrOO: the Brazilian Portuguese Grammar Checker
This paper highlights the main results obtained in an effort to improve the grammar checker CoGrOO, a hybrid system which initially annotates the text using statistical Natural Language Processing (NLP) techniques, and then apply a rule-based analysis to identify possible grammar errors. The goal was to reduce omissions and false alarms while improving true positives without adding new error ru...
متن کاملReducing Overdetections in a French Symbolic Grammar Checker by Classification
We describe the development of an “overdetection” identifier, a system for filtering detections erroneously flagged by a grammar checker. Various families of classifiers have been trained in a supervised way for 14 types of detections made by a commercial French grammar checker. Eight of these were integrated in the most recent commercial version of the system. This is a striking illustration o...
متن کامل