Machine Translation and Computational Linguistics Resources


	Companion Main
	Translation News
	International News
	Glossaries
	Translation Engines
	Other Resources
	Tools Garage™
	Translation Products
	Find a Translator
	Find a Job
	Organizations
	Translation Agencies
	Education
	Confs/Seminars
	Partners/Contributors

		machine translation and computational linguistics resources About Machine Translation The purpose of this site is to re-establish the truth about the real (im)possibilities of Machine Translation systems (also called automatic translators). Asia-Pacific Association for Machine Translation (AAMT) The Association for Computational Linguistics The BabelCode Project - controlled language research Compendium of translation software published by the EAMT Computational Linguistics/Language Engineering Resources Computational Linguistics Resources (Stanford University) Controlled Language article This article discusses adapting the concept of "Translation Memory" to "Authoring memory" for a Controlled Language writing environment. It was presented by Jeff Allen at the 21st Conference of "Translating and the Computer", sponsored by ASLIB, 10-11 November 1999, London. The EMILLE project EMILLE (Enabling Minority Language Engineering) is a 3 year EPSRC project at Lancaster University and Sheffield University, designed to build a 63 million word electronic corpus of South Asian languages, especially those spoken in the UK. Euralex - European Association for Lexicography Euromap articles on machine translation and language technology The European Association for Machine Translation FEMTI, the Framework for Machine Translation Evaluation in ISLE FEMTI is a structured repertoire of methods used to evaluate MT systems. The first part of FEMTI enables evaluators to specify a context of use for the MT system to be evaluated, while the second part defines relevant quality characteristics and metrics. FEMTI is a result of the ISLE Project, funded by the US National Science Foundation and the Swiss and Danish Governments. See also the Van Slype report, below. German Morphology Browser The German Morphology Browser is powered by the WordManager Transducer Toolkit. The program knows 1.2 million German words, their morphosyntactic features, and their mapping to some 130'000 lexemes. In addition, it contains all relationships between simple and complex lexemes. Out of the 130'000 lexemes, only 13.4% are simple. The other entries are complex and are constructed out of simple lexemes. This resource serves as basis for various innovative Web applications as e.g. in the areas of Language Learning, Information Retrieval, Hyperlink Generation. Like other forthcoming Language Products of the Canoo Engineering AG the German Morphology Browser is based on a cooperation with University of Basel, Vrije Universiteit Amsterdam, and IDSIA Lugano. History of MT Long, thorough review of machine translation's past and especially of its exciting current developments. Human Translation versus Machine Translation and Full Post-Editing of Raw Machine Translation Output. Master's Thesis by Lorena Guerra (2003) IMS Stuttgart list of Institutes active in the areas of Computational Lingustics and Natural Language Processing, also various resources IMS Stuttgart - Machine Translation Overview The KANT project - Controlled language technology developed at CMU Language Technology newletter published by the government of India Latin American Registry of Researchers in Natural Language Processing and Computational Linguistics List of CAT tools, MT software and companies, on-line publications, MT engines List of MT companies, products, prices Machine Translation Bibliography (books and publications by John Hutchins) Machine Translation in African Languages Machine Translation Post-editing Information Web Site (courtesy Jeff Allen) This Web site primarily focuses on providing links to articles on the use of Machine Translation postediting, although there are also many links to machine translation in general, machine translation software reviews, speech technologies, controlled language authoring systems, translation memory tools, etc. MT-Grid: list of on-line MT engines MT Summit IX Conference (the latest) Presentations/Papers Multiconcord, Multilingual Parallel Concordancer Multiconcord is a Multilingual Parallel Concordancer which operates in all Western European Languages, including Greek, and a version which operates in addition in Central European languages and Russian. There is also a version which offers tri-lingual concordancing in Chinese/Pinyin and English which works if Chinese is available on the computer. Multilingual Computing and Technology Magazine (searchable archive of articles on MT and translation technology) Natural Language Software Registry The Natural Language Software Registry (NLSR) is a concise summary of the capabilities and sources of a large amount of natural language processing (NLP) software available to the NLP community. NTT Machine Translation Research Group The NTT Machine Translation Research Group carries out research into Natural Language Processing, centered on the development of ALT-J/E, a practical Japanese-to-English machine translation system based on semantic analysis. No Limits No Limits is a new website dedicated to the subject of machine translation. The site covers history, analysis, speculations on the future of MT, tons of usable and off-the-beaten-track resources which are constantly updated. The author emphasizes the commercial aspect of machine translation. OLIF - Open Lexicon Information Format OLIF, the Open Lexicon Interchange Format, is a user-friendly vehicle for exchanging terminological and lexical data. OLIF is XML-compliant and offers support for natural language processing (NLP) systems, such as machine translation, by providing coverage of a wide and detailed range of linguistic features. Overview of Example-based Machine Translation by Harold Somers Parallel texts for MT evaluation (courtesy Debbie Elliott, University of Leeds) Prospector - list of on-line MT engines Publications by Jeff Allen on Machine Translation, Postediting, Controlled language and related topics Resources for evaluating MT systems (by ISI) Russian text corpus Stemming algorithms for various European languages TransSearch, the RALI's bilingual concordancing tool TransSearch is a bilingual concordancing tool. It was originally developped by the Computer-Aided Translation (CAT) research team of the Centre for Information Technology Innovation (CITI). This team now constitutes the core of the RALI laboratory. Word2Word's machine translation list Van Slype 1979 report on MT evaluation (see the Working Group documents) This report contains valuable analyses of criteria for MT evaluation, and was produced for the European Community by synthesizing the contributions of a wide set of experts. Please send comments, requests and submissions to the Webmaster Copyright © 1994-2004, Language Automation, Inc. All rights reserved.