Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Grammar Lost Translation Machine In Researchers Fix Will

12.09.2005


The makers of a University of Southern California computer translation system consistently rated among the world’s best are teaching their software something new: English grammar.



Most modern "machine translation" systems, including the highly rated one created by USC’s Information Sciences Institute, rely on brute force correlation of vast bodies of pre-translated text from such sources as newspapers that publish in multiple languages.
Software matches up phrases that consistently show up in parallel fashion — the English "my brother’s pants" and Spanish "los pantalones de mi hermano," — and then use these matches to piece together translations of new material.

It works — but only to a point. ISI machine translation expert Daniel Marcu (left) says that when such a system is "trained on enough relevant bilingual text ... it can break a foreign language up into phrasal units, translate each of them fairly well into English, and do some re-ordering. However, even in this good scenario, the output is still clearly not English. It takes too long to read, and it is unsatisfactory for commercial use."



So Marcu and colleague Kevin Knight (right), both ISI project leaders who also hold appointments in the USC Viterbi School of Engineering department of computer science, have begun an intensive $285,000 effort, called the Advanced Language Modeling for Machine Translation project, to improve the system they created at ISI by subjecting the texts that come out of their translation engine to a follow-on step: grammatical processing.

The step seems simple, but is actually imposingly difficult. "For example, there is no robust algorithm that returns ’grammatical’ or ’ungrammatical’ or ’sensible’ or ’nonsense’ in response to a user-typed sequence of words," Marcu notes.

The problem grows out of a natural language feature noted by M.I.T. language theorist Noam Chomsky decades ago. Language users have literally a limitless ability to nest and cross-nest phrases and ideas into intricate referential structures — "I was looking for the stirrups from the saddle that my ex-wife’s oldest daughter took with her when she went to Jack’s new place in Colorado three years ago, but all she had were Louise’s second-hand saddle shoes, the ones Ethel’s dog chewed during the fire."

Unraveling these verbal cobwebs (or, in the more common description, tracing branching "trees" of connections) is such a daunting task that programmers long ago went in the brute force direction of matching phrases and hoping that the relation of the phrases would become clear to readers.

With the limits of this approach becoming clear, researchers have now begun applying computing power to trying to assemble grammatical rules. According to Knight, one crucial step has been the creation of a large database of English text whose syntax has been hand-decoded by humans, the "Penn Treebank."

Using this and other sources, computer scientists have begun developing ways to model the observed rules. A preliminary study by Knight and two colleagues in 2003 showed that this approach might be able to improve translations.

Accordingly, for their study, "We propose to implement a trainable tree-based language model and parser, and to carry out empirical machine-translation experiments with them. USC/ISI’s state-of-the-art machine translation system already has the ability to produce, for any input sentence, a list of 25,000 candidate English outputs. This list can be manipulated in a post-processing step. We will re-rank these lists of candidate string translations with our tree- based language model, and we plan for better translations to rise to the top of the list."

One crucial trick that the system must be able to do is to pick out separate trees from the endless strings of words. But this is doable, Knight believes -- and in the short, not the long term.

Referring to the annual review of translation systems by the National Institute of Science and Technology, in which ISI consistently gains top scores, "we want to have the grammar module installed and working by the next evaluation, in August 2006," he said.

Knight and Marcu are cofounders and, respectively, chief scientist and chief technology and operating officer of a spinoff company, Language Weaver.

Eric Mankin | EurekAlert!
Further information:
http://www.usc.edu

More articles from Information Technology:

nachricht Fingerprints of quantum entanglement
16.02.2018 | University of Vienna

nachricht Simple in the Cloud: The digitalization of brownfield systems made easy
07.02.2018 | Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: Demonstration of a single molecule piezoelectric effect

Breakthrough provides a new concept of the design of molecular motors, sensors and electricity generators at nanoscale

Researchers from the Institute of Organic Chemistry and Biochemistry of the CAS (IOCB Prague), Institute of Physics of the CAS (IP CAS) and Palacký University...

Im Focus: Hybrid optics bring color imaging using ultrathin metalenses into focus

For photographers and scientists, lenses are lifesavers. They reflect and refract light, making possible the imaging systems that drive discovery through the microscope and preserve history through cameras.

But today's glass-based lenses are bulky and resist miniaturization. Next-generation technologies, such as ultrathin cameras or tiny microscopes, require...

Im Focus: Stem cell divisions in the adult brain seen for the first time

Scientists from the University of Zurich have succeeded for the first time in tracking individual stem cells and their neuronal progeny over months within the intact adult brain. This study sheds light on how new neurons are produced throughout life.

The generation of new nerve cells was once thought to taper off at the end of embryonic development. However, recent research has shown that the adult brain...

Im Focus: Interference as a new method for cooling quantum devices

Theoretical physicists propose to use negative interference to control heat flow in quantum devices. Study published in Physical Review Letters

Quantum computer parts are sensitive and need to be cooled to very low temperatures. Their tiny size makes them particularly susceptible to a temperature...

Im Focus: Autonomous 3D scanner supports individual manufacturing processes

Let’s say the armrest is broken in your vintage car. As things stand, you would need a lot of luck and persistence to find the right spare part. But in the world of Industrie 4.0 and production with batch sizes of one, you can simply scan the armrest and print it out. This is made possible by the first ever 3D scanner capable of working autonomously and in real time. The autonomous scanning system will be on display at the Hannover Messe Preview on February 6 and at the Hannover Messe proper from April 23 to 27, 2018 (Hall 6, Booth A30).

Part of the charm of vintage cars is that they stopped making them long ago, so it is special when you do see one out on the roads. If something breaks or...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

2nd International Conference on High Temperature Shape Memory Alloys (HTSMAs)

15.02.2018 | Event News

Aachen DC Grid Summit 2018

13.02.2018 | Event News

How Global Climate Policy Can Learn from the Energy Transition

12.02.2018 | Event News

 
Latest News

Fingerprints of quantum entanglement

16.02.2018 | Information Technology

'Living bandages': NUST MISIS scientists develop biocompatible anti-burn nanofibers

16.02.2018 | Health and Medicine

Hubble sees Neptune's mysterious shrinking storm

16.02.2018 | Physics and Astronomy

VideoLinks
Science & Research
Overview of more VideoLinks >>>