Sixth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-6)

ACL 2012 / SIGMT / SIGLEX Workshop
12 July 2012, Jeju, Korea

The Sixth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-6) seeks to build on the foundations established in the first five SSST workshops, which brought together a large number of researchers working on diverse aspects of structure, semantics and representation in relation to statistical machine translation. Its program each year has comprised high-quality papers discussing current work spanning topics including: new grammatical models of translation; new learning methods for syntax- and semantics-based models; formal properties of synchronous/transduction grammars (hereafter S/TGs); discriminative training of models incorporating linguistic features; using S/TGs for semantics and generation; and syntax- and semantics-based evaluation of machine translation.

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 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.

At the same time, SMT has seen a movement toward semantics over the past few years, which has been reflected at recent SSST workshops, including the last edition which had semantics for SMT as a special theme. The issues of deep syntax and shallow semantics are closely linked and SSST-6 encourages submissions on semantics for MT in a number of directions, including semantic role labeling (SRL) for SMT, WSD for SMT and in particular, semantics for MT evaluation. In order to emphasize the need to evaluate MT in a way that properly assesses preservation of structure and semantics, SSST-6 is highlighting Semantic MT Evaluation as a special workshop theme.

We invite papers on:

syntactically- and semantically-motivated evaluation of MT
syntax-based / semantics-based / tree-structured SMT
machine learning techniques for inducing structured translation models
algorithms for training, decoding, and scoring with semantic representation structure
empirical studies on adequacy and efficiency of formalisms
creation and usefulness of syntactic/semantic resources for MT
formal properties of synchronous/transduction grammars
learning semantic information from monolingual, parallel or comparable corpora
unsupervised and semi-supervised word sense induction and disambiguation methods for MT
lexical substitution, word sense induction and disambiguation, semantic role labeling, textual entailment, paraphrase and other semantic tasks for MT
semantic features for MT models (word alignment, translation lexicons, language models, etc.)
evaluation of syntactic/semantic components within MT (task-based evaluation)
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
syntactically- and semantically-motivated evaluation of MT

For more information: http://www.cs.ust.hk/~dekai/ssst/

Special Theme: Semantics MT Evaluation

Ongoing work suggests that MT evaluation is improved by generalizing across similar word meanings (Zhou et al., 2006; Apidianaki et al, 2009; Snover et al., 2009; Denkowski and Lavie, 2010), and explicitly modeling preservation of meaning with textual entailment (Padó et al. 2009), or semantic frames (Lo and Wu, 2011). However, crucial questions such as what frameworks are best suited to measure MT quality in general, and the impact of semantic modeling in MT evaluation remain unanswered. With this year's special theme, we seek to bring together researchers working on semantics and on translation evaluation in order to encourage cross-pollination of ideas, share insights into the needs of MT evaluation and what current developments in semantics have to offer. We particularly encourage the submission of papers addressing the following issues related to semantics-driven evaluation of MT:

MT evaluation metrics generalizing across similar word meanings
MT evaluation metrics explicitly modeling preservation of meaning via textual entailment, semantic frames, etc
New frameworks to measure MT quality using semantic information, including machine learning approaches
Evaluation of the impact of semantic modeling on MT evaluation
Use of semantic information for quality/confidence estimation (MT evaluation without reference translations)

Organizers

Marine CARPUAT, National Research Council (NRC), Canada
Lucia SPECIA, University of Sheffield, UK
Dekai WU, Hong Kong University of Science and Technology (HKUST), Hong Kong

Program Committee

Marianna APIDIANAKI, LIMSI-CNRS, France
Wilker AZIZ, University of Wolverhampton, UK
Srinivas BANGALORE, AT&T Research, USA
David CHIANG, USC ISI, USA
Colin CHERRY, National Research Council (NRC), Canada
Mona DIAB, Columbia University, USA
Alexander FRASER, University of Stuttgart, Germany
Daniel GILDEA, University of Rochester, USA
Nizar HABASH, Columbia University, USA
Yifan HE, Dublin City University, Ireland
Philipp KOEHN, University of Edinburgh, UK
Kevin KNIGHT, USC ISI, USA
Alon LAVIE, Carnegie Mellon University, USA
Yanjun MA, Baidu, China
Daniel MARCU, USC ISI and Language Weaver, USA
Lluìs MÀRQUEZ, Universitat Politècnica de Catalunya, Spain
Sudip Kumar NASKAR, Dublin City University, Ireland
Hwee Tou NG, National University of Singapore, Singapore
Daniel PIGHIN, Universitat Politècnica de Catalunya, Spain
Markus SAERS, Hong Kong University of Science and Technology (HKUST), Hong Kong
Libin SHEN, IBM, USA
Matthew SNOVER, BBN, USA
John TINSLEY, Dublin City University, Ireland
Stephan VOGEL, Carnegie Mellon University, USA
Taro WATANABE, NICT, Japan
Deyi XIONG, National University of Singapore, Singapore
François YVON, Université Paris Sud 11, France

Important Dates

Submission deadline: 27 Apr 2012
Notification to authors: 16 May 2012
Camera copy deadline: 23 May 2012

Submission

Papers will be accepted on or before 27 Apr 2012 in PDF or Postscript formats via the START system at https://www.softconf.com/acl2012/ssst-6/. Submissions should follow the ACL 2012 length and formatting requirements for long papers of eight (8) pages of content with two (2) additional pages of references, found at http://www.acl2012.org/call/sub01.asp.

Camera Copy

Camera ready final versions will be accepted on or before 23 May 2012 in PDF or Postscript formats via the START system at https://www.softconf.com/acl2012/ssst-6/. Papers should follow the ACL 2012 camera ready length and formatting requirements for long papers of eight (8) pages of content with two (2) additional pages of references, found at http://www.acl2012.org/call/sub01.asp.

Contact

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