SYNTAX AND STRUCTURE IN STATISTICAL TRANSLATION (SSST)

 

NAACL-HLT 2007 Workshop

Rochester, New York, 26 April 2007

 

The need for structural mappings between languages is widely

recognized in the fields of statistical machine translation and spoken

language translation, and there is a growing consensus that these

mappings are appropriately represented using a family of formalisms

that includes synchronous/transduction grammars (hereafter, S/TGs) and

their tree-transducer equivalents. To date, flat-structured models,

such as the word-based IBM models of the early 1990s or the more

recent phrase-based models, remain widely used. But tree-structured

mappings arguably offer a much greater potential for learning valid

generalizations about relationships between languages.

 

Within this area of research there is a rich diversity of approaches.

There is active research ranging from formal properties of S/TGs to

large-scale end-to-end systems. There are approaches that make heavy

use of linguistic theory, and approaches that use little or none.

There is theoretical work characterizing the expressiveness and

complexity of particular formalisms, as well as empirical work

assessing their modeling accuracy and descriptive adequacy across

various language pairs. There is work being done to invent better

translation models, and work to design better algorithms. Recent years

have seen significant progress on all these fronts. In particular,

systems based on these formalisms are now top contenders in MT

evaluations.

 

In response to this bustling new situation, the workshop on Syntax and

Structure in Statistical Translation (SSST) seeks to bring together

researchers working on diverse aspects of S/TGs in relation to

statistical machine translation, to discuss current work, compare and

contrast different approaches, and identify the questions that are

most pressing for future progress in this area.

 

We invite papers on:

 

* syntax-based / tree-structured statistical translation models

* machine learning techniques for inducing structured translation models

* algorithms for training, decoding, and scoring with S/TGs

* empirical studies on adequacy and efficiency of formalisms

* studies on the usefulness of syntactic resources for translation

* formal properties of S/TGs

* scalability of structured translation methods to small or large data

* applications of S/TGs to related areas including:

  - speech translation

  - formal semantics and semantic parsing

  - paraphrases and textual entailment

  - information retrieval and extraction

 

For details and submission information please see:

  http://www.cs.ust.hk/~dekai/ssst/

 

ORGANIZERS

 

Dekai Wu (Hong Kong University of Science and Technology)

David Chiang (USC Information Sciences Institute)

 

PROGRAM COMMITTEE (partial)

 

Srinivas Bangalore (AT&T Research)

Daniel Gildea (University of Rochester)

Kevin Knight (USC Information Sciences Institute)

Daniel Marcu (USC Information Sciences Institute)

Hermann Ney (RWTH Aachen)

Owen Rambow (Columbia University)

Philip Resnik (University of Maryland)

Giorgio Satta (University of Padua)

Stuart Shieber (Harvard University)

Christoph Tillmann (IBM)

Enrique Vidal (Universidad Politecnica de Valencia)

Stephan Vogel (Carnegie Mellon University)

Taro Watanabe (NTT)

Andy Way (Dublin City University)

Richard Zens (RWTH Aachen)

 

CONTACT

 

Please send inquiries to ssst@cs.ust.hk.

========================================


NAACL HLT 2007 Workshop:
Syntax and Structure in Statistical Translation (SSST)

Tree-structured mappings between languages are widely recognized as
desirable for statistical machine translation, and there is mounting
interest in approaches built on a family of formalisms that includes
synchronous/transduction grammars and their tree transducer
equivalents. From this formal basis, there has been rapid progress on
many different fronts, ranging from purely mathematical results to
very strong showings in large-scale evaluations. The workshop on
Syntax and Structure in Statistical Translation seeks to bring
together researchers working on diverse aspects of
synchronous/transduction grammars in relation to statistical machine
translation, to build stronger connections in this area and stimulate
further progress.

Organizers:

 Dekai Wu, HKUST
 David Chiang, ISI/USC

Paper submissions due: January 5

Workshop Home Page:

    http://www.cs.ust.hk/~dekai/ssst/