Machine Translation

AI Methods forTranslating from One Language to Another

"A renewed international effort is gearing up to design computers and software that smash language barriers and create a borderless global marketplace."
- Steve Silberman

"What is Machine Translation? Machine translation (MT) is the application of computers to the task of translating texts from one natural language to another. One of the very earliest pursuits in computer science, MT has proved to be an elusive goal, but today a number of systems are available which produce output which, if not perfect, is of sufficient quality to be useful in a number of specific domains."
- Definition from the European Association for Machine Translation (EAMT).

You can translate text of your choice by using free translators such as:

Natural Language

Contents

Vertical Tabs

Good Starting Places

AI in the News

Google Translate

It already speaks 57 languages as well as a 10-year-old. Newer methods dominated by Google turn the problem around: Using data, statistics, and brute force, they succeed in part by their refusal to "deconstruct" language and teach meaning to computers in the traditional way. Google is grossly outperforming the rule-based methods that have historically been used to teach language to computers. These classic methods work on the principle that language can be decoded, stripped to its purest component parts of "meaning," and built back up again into another language.

Source

Oct 31 2011, By Kingsley, Jeremy
statistical
Link

Talking to Strangers.

By Steve Silberman. Wired (May 2000; 8.05). "A renewed international effort is gearing up to design computers and software that smash language barriers and create a borderless global marketplace."

Source

2005
Link

Machine Translation: an Introductory Guide

By Doug Arnold, Lorna Balkan, Siety Meijer, R.Lee Humphreys and Louisa Sadler (1994). "The topic of the book is the art or science of Automatic Translation, or Machine Translation (MT) as it is generally known --- the attempt to automate all, or part of the process of translating from one human language to another. The aim of the book is to introduce this topic to the general reader --- anyone interested in human language, translation, or computers."

Source

1994
Link

NIST Open Machine Translation (OpenMT) Evaluation

"The objective of the NIST Open Machine Translation (OpenMT) evaluation series is to support research in, and help advance the state of the art of, machine translation (MT) technologies - technologies that translate text between human languages. Input may include all forms of text. The goal is for the output to be an adequate and fluent translation of the original." Includes results back as far as 2001.

Source

General Readings

AI in the News

Software Translates Your Voice into Another Language

Researchers at Microsoft have made software that can learn the sound of your voice, and then use it to speak a language that you don't. In a demonstration at Microsoft's Redmond, Washington, campus on Tuesday, Microsoft research scientist Frank Soong showed how his software could read out text in Spanish using the voice of his boss, Rick Rashid, who leads Microsoft's research efforts. Hear Rick Rashid's voice in his native language and then translated into several other languages: In English, a synthetic version of Mundie's voice welcomed the audience to an open day held by Microsoft Research, concluding, "With the help of this system, now I can speak Mandarin. " Individual sounds used by the first model to build up words using a person's voice in his or her own language are carefully tweaked to give the new text-to-speech model a full ability to sound out phrases in the second language.

Source

Mar 9 2012, By Simonite, Tom
microsoft, speech generation
Publication

Google Translate in the Office

The potential usefulness of automatic computerized translation was recognized by the very first AI researchers in the 1950s. The poster child for computer translation is Google Translate, the easy-to-use, general purpose Web-based translation engine that can handle nearly 60 languages. And as home computer users being appreciating the accuracy of Google Translate for casual Web surfinglike reading foreign newspapers when big breaking stories occur they will bring those habits with them to the office and start doing the same thing at work. American intelligence agencies, notoriously short on translators for strategically crucial languages like Farsi and Arabic, are already power users of machine translation technologies like Google's, which they rely on to quickly decide if, say, a website deserves closer study.

Source

Aug 24 2011, By Gomes, Lee
Google
Publication

Tigris and Euphrates: A comparison between human and machine translation

Source

By Richens, R.H., 1959,
classic
Link

Machine Translation's Past and Future

A timeline from Wired covering the span from 1629 through the year 2264! Compiled by Kristin Demos and Mark Frauenfelder.

Source

Link

Machine Translation for Manufacturing---A Case Study at Ford Motor Company

By Nestor Rychtyckyj. AI Magazine 28(3): Fall 2007, 31. "Machine translation (MT) was one of the first applications of artificial intelligence technology that was deployed to solve real-world problems. Since the early 1960s, researchers have been building and utilizing computer systems that can translate from one language to another without requiring extensive human intervention. In the late 1990s, Ford Vehicle Operations began working with Systran Software Inc. to adapt and customize its machine-translation technology in order to translate Fords vehicle assembly build instructions from English to German, Spanish, Dutch, and Portuguese. The use of machine translation was made necessary by the vast amount of dynamic information that needed to be translated in a timely fashion. The assembly build instructions at Ford contain text written in a controlled language as well as unstructured remarks and comments. The MT system has already translated more than 7 million instructions into these languages and is an integral part of the overall manufacturing process-planning system used to support Fords assembly plants in Europe, Mexico and South America. In this paper, we focus on how AI techniques, such as knowledge representation and natural language processing can improve the accuracy of machine translation in a dynamic environment such as auto manufacturing."

Source

Organizations

Link

Center for Computational Learning Systems

Part of the Columbia Center for Computational Learning Systems (CCLS) at Columbia University.

Source

Link

The DePaul University American Sign Language Project

"Combining computer technology and linguistics research to bridge the communication gap between the deaf and hearing worlds, our team of deaf and hearing researchers is working towards the realization of a digital English-to-ASL translator."

Source

Link

Association for Machine Translation in the Americas

"AMTA is an association dedicated to anyone interested in the translation of languages using computers in some way. This includes people with translation needs, commercial system developers, researchers, sponsors, and people studying, evaluating, and understanding the science of machine translation (MT) and educating the public on important scientific techniques and principles involved.... AMTA has members in Canada, Latin America, and the United States. It is the regional component of a worldwide network headed by the International Association for Machine Translation (IAMT)."

Source

Link

The International Center for Advanced Communication Technologies (InterACT)

"a network of leading Research Universities and Institutes of the main economies of the world. It has a dual mission:

  • Advanced research on technologies that support and facilitate global communication, cooperation and exchange.
  • Training/Education of scientists in an environment of scientific excellence, while at the same time providing immersion and experience working in a multicultural and multilingual setting."

Source

Link

European Association for Machine Translation (EAMT)

The European Association for Machine Translation (EAMT) is 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.

Source

Link

Language Technologies Institute

"The Language Technologies Institute (LTI) at Carnegie Mellon University (CMU) conducts extensive research on Computational Linguistics, Machine Translation,Speech Recognition and Synthesis, Information Retrieval, Computational Biology,Machine Learning, Text Mining, Knowledge Representation, Computer-Assisted Language Learning and Intelligent Language Tutoring."

Source

Educational Resources

Link

Mechanical Translation and Computational Linguistics

Bibliography of articles 1954-1970.

 

bibliography, collection

Hardware and Software

AI in the News

Microsoft demos speech translator

Software that can translate spoken English into spoken Chinese almost instantly has been demonstrated by Microsoft. The software preserves intonation and cadence so the translated speech still sounds like the original speaker.

Source

Nov 9 2012
chinese, microsoft

News

AI in the News

Microsoft demos speech translator

Software that can translate spoken English into spoken Chinese almost instantly has been demonstrated by Microsoft. The software preserves intonation and cadence so the translated speech still sounds like the original speaker.

Source

Nov 9 2012
chinese, microsoft
AI in the News

DARPA grant to support research into auto-translation of Chinese

While emerging technologies such as Google Translate have shown promise, much work must be done to improve the language translation applications that America will need as one of its most important 21st century relationships develops. To move the technology forward, the Defense Advanced Research Projects Agency (DARPA) has awarded a $13.7 million grant, called Linguistic Resources for Multilingual, Genre-Independent Language Technologies via its Broad Operational Language Translation (BOLT) Program to the Linguistic Data Consortium at the University of Pennsylvania to develop linguistic resources. Xue has been involved in this research program for years, beginning with Translingual Information Detection, Extraction and Summarization (TIDES) then Global Autonomous Language Exploitation ( GALE ), a five-year program that he worked on while at the University of Colorado. According to DARPA, BOLT is part of a broader effort to provide language translation in support of defense and national security requirements, ranging from phrase translation to scanning and translation of large data sets......

Source

Apr 5 2012
AI in the News

Software Translates Your Voice into Another Language

Researchers at Microsoft have made software that can learn the sound of your voice, and then use it to speak a language that you don't. In a demonstration at Microsoft's Redmond, Washington, campus on Tuesday, Microsoft research scientist Frank Soong showed how his software could read out text in Spanish using the voice of his boss, Rick Rashid, who leads Microsoft's research efforts. Hear Rick Rashid's voice in his native language and then translated into several other languages: In English, a synthetic version of Mundie's voice welcomed the audience to an open day held by Microsoft Research, concluding, "With the help of this system, now I can speak Mandarin. " Individual sounds used by the first model to build up words using a person's voice in his or her own language are carefully tweaked to give the new text-to-speech model a full ability to sound out phrases in the second language.

Source

Mar 9 2012, By Simonite, Tom
microsoft, speech generation
AI in the News

Google Translate

It already speaks 57 languages as well as a 10-year-old. Newer methods dominated by Google turn the problem around: Using data, statistics, and brute force, they succeed in part by their refusal to "deconstruct" language and teach meaning to computers in the traditional way. Google is grossly outperforming the rule-based methods that have historically been used to teach language to computers. These classic methods work on the principle that language can be decoded, stripped to its purest component parts of "meaning," and built back up again into another language.

Source

Oct 31 2011, By Kingsley, Jeremy
statistical
AI in the News

A website that hopes to speak the language of freely available data

Flummoxed by a document in Welsh? Now you can get a free translation at cymraeg.org.uk. The Apertium-cy software, described as the first free automatic translator from Welsh to English, is the fruit of a multilingual effort involving developers in Spain, Wales and Ireland pushing forward the possibilities of open-source software and, they hope, free public-sector data. ... Work on the Welsh-language version was led by Francis Tyers and Kevin Donnelly. It contains about 10,000 words in Welsh and English and 150 grammatical rules - enough to get the gist of the text, the developers say. The idea is to provide an easy way for people who don't speak Welsh to keep an eye on Welsh-language media reports in an area of interest, and to provide a "first-pass" translation of documents, improving the productivity of human translators.

Source

Aug 14 2008

Videos

Video

A panel discussion about Artificial Intelligence

The Charlie Rose Show: A panel discussion about Artificial Intelligence (December 21, 2004), with Rodney Brooks (Director, MIT Artificial Intelligence Laboratory Fujitsu Professor of Computer Science Engineering, MIT), Eric Horvitz (Senior Researcher and Group Manager, Adaptive Systems Interaction Group, Microsoft Research), and Ron Brachman (Director, Information Processing Technology Office, Defense Advanced Research Project Agency, and President, American Association for Artificial Intelligence).

"Rose: What do you think has been the most important advance so far? Brachman: A lot of people will vary on that and I'm sure we all have different opinions. In some respects one of the - - - I think the elemental insights that was had at the very beginning of the field still holds up very strongly which is that you can take a computing machine that normally, you know, back in the old days we think of as crunching numbers, and put inside it a set of symbols that stand in representation for things out in the world, as if we were doing sort of mental images in our own heads, and actually with computation, starting with something that s very much like formal logic, you know, if-then-else kinds of things, but ultimately getting to be softer and fuzzier kinds of rules, and actually do computation inside, if you will, the mind of the machine, that begins to allow intelligent behavior. I think that crucial insight, which is pretty old in the field, is really in some respects one of the lynch pins to where we've gotten....

Horvitz: I think many passionate researchers in artificial intelligence are fundamentally interested in the question of Who am I? Who are people? What are we? There's a sense of almost astonishment at the prospect that information processing or computation, if you take that perspective, could lead to this. Coupled with that is the possibility of the prospect of creating consciousnesses with computer programs, computing systems some day. It's not talked about very much at formal AI conferences, but it's something that drives some of us in terms of our curiosity and intrigue. I know personally speaking, this has been a core question in the back of my mind, if not the foreground, not on my lips typically, since I've been very young. This is this question about who am I.

Rose:... can we create it?

Horvitz: Is it possible - - - is it possible that parts turning upon parts could generate this?"

---

Watch Ron Brachman demonstrate the Phraselator. The segment begins at 20:34.

Source

25 min, 2004

Classic Articles & Books

Pages

Publication

The Thesaurus in Syntax and Semantics

The recent work of the Unit has been primarily concerned with the employment of
thesauri in machine translation. Limited success has been achieved, in punchedcard
tests, in improving the idiomatic quality and so the intelligibility of an initially
unsatisfactory translation, by word-for-word procedures, from Italian into
English, by using a program which permitted selection of final equivalents from
"heads" in Roget's Thesaurus, i.e. lists of synonyms, near-synonyms and associated
words and phrases, instead of from previously determined lists of alternative
translations.

Source

By Masterman, M.M., 1957
classic
Publication

Semantic Message Detection for Machine Translation, Using an Interlingua

In my view, the present "critical situation" in M.T., is not due to
the fact that genuine Mechanical Translation is inherently impossible, as
Bar-Hillel thinks,  but to the fact that the mechanizable techniques at
present being used to analyse language are not powerful enough to detect
the message, or argument, of any particular text.

Other papers from this conference online.  See Table of Contents with links to online papers from the Proc. 1961 International Conference on Machine Translation of Languages and Applied Language Analysis,

 

Source

By Masterman, Margaret, 1962
classic
Publication

Tigris and Euphrates: A comparison between human and machine translation

Source

By Richens, R.H., 1959,
classic
Publication

An artificial intelligence approach to machine translation

Source

By Wilks, Y. A. , 1973
classic
Publication

Methodological questions about artificial intelligence: Approaches to understanding natural language

From Sedlow, Walter A., et al. (eds.) Computers in Language Research 2: Berlin: Degruiter & Co, 1983

Source

By Wilks, Y. A. , 1983
SHRDLU, classic, history, overview
Publication

Translation

Source

By Weaver, W. , 1949
classic

Pages

Vertical Tabs