Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8)
EMNLP 2014 / SIGMT / SIGLEX
Workshop
25 Oct 2014, Doha, Qatar
*** [NEW] Slides for all papers below ***
*** Special theme: Compositional Distributional Semantics and Machine Translation ***
The Eighth Workshop on Syntax, Semantics and Structure in Statistical
Translation (SSST-8) 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 this year:
- Extended abstracts for poster or hands-on presentations on the special theme
- Full papers spanning all areas of interest for SSST
This year, the special theme of semantics of the past three editions of SSST takes a new step with a "working workshop" bringing together researchers interested in compositional distributional semantics, distributed representations, and continuous vector space models in MT, with tutorials bridging both directions, as well as discussions and hands-on work on relevant tasks with real data. Such models have proven beneficial for a number of NLP tasks, for example phrasal similarity, lexical entailment, modeling semantic deviance, detecting order restrictions in recursive structures, or improving NP bracketing in parsing. However, they have not received as much attention in MT.
Extended abstracts of at most two (2) pages should describe poster or hands-on presentations that will stimulate discussions on the special theme of compositional distributional semantics and machine translation, including position papers, recent work, pilot studies, negative results. We encourage the presentation of relevant work that has been published or submitted elsewhere, as well as new work in progress.
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-8 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:
- 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
- compositional distributional semantics in MT
- distributed representations and continuous vector space models in MT
|
|
| 09:00–09:10 |
Opening remarks
Dekai Wu, Marine Carpuat, Xavier Carreras, Eva Maria
Vecchi |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11:00–12:00 |
Composed, Distributed Reflections on Semantics and
Statistical Machine Translation [slides]
Timothy Baldwin |
|
| Session 2: Morning Spotlights |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Session 3: Afternoon Orals and Spotlights
|
|
|
|
|
|
|
|
| 15:00–15:20 |
Transformation
and Decomposition for Efficiently Implementing and Improving
Dependency-to-String Model In Moses [slides]
Liangyou Li1, Jun Xie2, Andy
Way3, Qun Liu4
1CNGL Centre for Global Intelligent Content, School
of Computing, Dublin City University, 2ICT,CAS,
3CNGL, Dublin City University, 4Dublin
City University |
|
|
|
|
|
|
|
| Session 4: Afternoon Spotlights |
|
|
|
|
|
|
|
|
|
| 16:15–17:30 |
Poster session of all workshop papers
All workshop presenters |
|
Submission deadline for papers and extended abstracts: 1 Aug 2014
Notification to authors: 26 Aug 2014
Camera copy deadline: 15 Sep 2014
Papers will be accepted on or before 1 Aug 2014 in PDF or Postscript
formats via the START system at https://www.softconf.com/emnlp2014/SSST-8/.
Submissions should follow the EMNLP 2014 length and formatting
requirements for long papers of nine (9) pages of content with any number of additional pages of references, found at http://emnlp2014.org/templates.html.
Please send inquiries to ssst@cs.ust.hk.
Last updated: 2014.10.25