Ninth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-9)

NAACL HLT 2015 / SIGMT / SIGLEX Workshop
4 Jun 2015, Denver, Colorado

*** [NEW] Full program below ***

*** QTLeap Best Paper Award - €500 Prize ***

The Ninth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-9) seeks to bring together a large number of researchers working on diverse aspects of structure, semantics and representation in relation to statistical machine translation. Since its first edition in 2006, 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.

We invite two types of submissions spanning all areas of interest for SSST:

Full Papers

The need for structural mappings between languages is widely recognized in the fields of statistical machine translation and spoken language translation, and there is now wide consensus that these mappings are appropriately represented using a family of formalisms that includes synchronous/transduction grammars and similar notational 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 three editions which had semantics for SMT as a special theme. The issues of deep syntax and shallow semantics are closely linked and SSST-9 continues to encourage submissions on semantics for MT in a number of directions, including semantic role labeling, sense disambiguation, and compositional distributional semantics for translation and evaluation.

We invite full papers on:

Best Paper Award

This year SSST-9 will award a best paper award among papers which advance MT using lexical semantics and deep language processing. This award is sponsored by the European Union QTLeap project. The winner of the prize will be announced at the workshop, and will win an Amazon voucher of €500.

Program

Invited Talk
Philipp Koehn
Harmonizing word alignments and syntactic structures for extracting phrasal translation equivalents
Dun Deng, Nianwen Xue, Shiman Guo
Brandeis University
Non-projective Dependency-based Pre-Reordering with Recurrent Neural Network for Machine Translation
Antonio Valerio Miceli Barone1 and Giuseppe Attardi2
1University of Pisa, Italy, 2Università di Pisa
Translating Negation: Induction, Search And Model Errors
Federico Fancellu and Bonnie Webber
University of Edinburgh
SMT error analysis and mapping to syntactic, semantic and structural fixes
Nora Aranberri
University of the Basque Country
Unsupervised False Friend Disambiguation Using Contextual Word Clusters and Parallel Word Alignments
Maryam Aminian1, Mahmoud Ghoneim2, Mona Diab1
1GWU, 2The George Washington University
METEOR-WSD: Improved Sense Matching in MT Evaluation
Marianna Apidianaki and Benjamin Marie
LIMSI-CNRS
Analyzing English-Spanish Named-Entity enhanced Machine Translation
Mikel Artetxe1, Eneko Agirre2, Iñaki Alegria2, Gorka Labaka2
1University of the Basque Country, 2University of the Basque Country (UPV/EHU)
Predicting Prepositions for SMT
Marion Weller1, Alexander Fraser2, Sabine Schulte im Walde3
1Universität Stuttgart, 2Ludwig-Maximilians-Universität München, 3University of Stuttgart
Translation reranking using source phrase dependency features
Antonio Valerio Miceli Barone
University of Pisa, Italy
Semantics-based pretranslation for SMT using fuzzy matches
Tom Vanallemeersch and Vincent Vandeghinste
Centre for Computational Linguistics, KU Leuven
What Matters Most in Morphologically Segmented SMT Models?
Mohammad Salameh1, Colin Cherry2, Grzegorz Kondrak1
1University of Alberta, 2NRC
Improving Chinese-English PropBank Alignment
Shumin Wu1 and Martha Palmer2
1University of Colorado Boulder, 2University of Colorado

Organizers

Important Dates

Submission deadline for papers and extended abstracts: 15 Mar 2015
Notification to authors: 24 Mar 2015
Camera copy deadline: 3 Apr 2015

Submission

Papers will be accepted on or before 15 Mar 2015 in PDF or Postscript formats via the START system at https://www.softconf.com/naacl2015/ssst-9/. Submissions should follow the NAACL HLT 2015 length and formatting requirements for long papers of eight (8) pages of content but allowing any number of additional pages of references, found at http://naacl.org/naacl-pubs/.

Camera Copy

Camera ready final versions will be accepted on or before 3 Apr 2015 in PDF or Postscript formats via the START system at https://www.softconf.com/naacl2015/ssst-9/. Papers should follow the NAACL HLT 2015 length and formatting requirements for long papers of eight (8) pages of content but allowing any number of additional pages of references, found at http://naacl.org/naacl-pubs/.

This workshop is partially funded by the European Union QTLeap project (FP7-ICT-2013-10-610516).

European Commission QTLeap

Contact

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

Last updated: 2015.05.06