| |||||||||||||||
S2MT 2015 : Semantics-Driven Statistical Machine Translation Theory and Practice | |||||||||||||||
Link: http://hlt.suda.edu.cn/workshop/s2mt/ | |||||||||||||||
| |||||||||||||||
Call For Papers | |||||||||||||||
**************************************************************
Call for Papers Semantics-Driven Statistical Machine Translation Theory and Practice (S2MT) Workshop in conjunction with ACL 2015, Beijing, China More info: http://hlt.suda.edu.cn/workshop/s2mt/ ************************************************************** Submission website: https://www.softconf.com/acl2015/S2MT =============== Important Dates =============== Paper submission: 14 May 2015 Notification of acceptance: 4 June 2015 Camera-ready papers due: 21 June 2015 Workshop: 30 July 2015 Overview -------- Over the last two decades, statistical machine translation (SMT) has made substantial progress from word-based to phrase and syntax-based SMT. Recently the progress curve has reached a stage where the performance growth of translation quality slows down even if we use sophisticated syntactic-forest-based models for translation. On the other hand, crucial meaning errors, such as incorrect translations of word senses and semantic roles, are still pervasive in SMT-generated translation hypotheses. These errors sometimes make the meanings of target translations significantly drift from the original meanings of source sentences. With an eye on the current dilemma of SMT, one might ask questions: Is SMT reaching the maturity stage of its lifespan? Or is it time for us to find a new direction for SMT in order to catalyze next breakthroughs? Semantics-driven SMT may be one of these breaking points. Semantics at different levels may enable SMT to generate not only grammatical but also meaning-preserving translations. Lexical semantics provides useful information for sense and semantic role disambiguation during translation. Compositional semantics allows SMT to generate target phrase and sentence translations by means of semantic composition. Discourse semantics captures inter-sentence dependencies for document-level machine translation. Large-scale semantic knowledge bases such as WordNet, YAGO and BabelNet can provide external semantic knowledge for SMT. Semantics-driven SMT allows us to gradually shift from syntax to semantics and offers insights on how meaning is correctly conveyed during translation. The goals of this workshop are to identify key challenges of exploring semantics in SMT, to discuss how semantics can help SMT and how SMT can benefit from rapid developments of semantic technologies theoretically and practically, and to find new opportunities emerging from the combination of semantics and SMT. Our key interest is to provide insights into semantics-driven SMT. Specifically, the motivations of this workshop are: - To bring researchers in the SMT and semantics community together and to cultivate new ideas for cutting-edge models and algorithms of semantic SMT. - To theoretically examine what semantics can provide for SMT and how SMT can benefit from semantics from a broad perspective. - To explore new research horizons for semantics-driven SMT in practice. Topics --------- Topics of interest include, but are not limited to: - Theoretic study of challenges, opportunities, pros and cons of exploring semantics in SMT - Linguistic semantics for Semantics-driven SMT - Lexical semantics, e.g., word sense disambiguation/induction, semantic roles - Compositional semantics - Linguistically-motivated representations of sentences in the context of SMT - Discourse semantics, e.g., cohesion, coherence, discourse relations - Distributional semantics for Semantics-driven SMT - Distributional lexical/compositional/sentential representations - Models and algorithms for learning bilingual/multilingual distributional semantics - Distributional approaches to compositional semantics for the purpose of SMT - Deep learning approaches to distributional-semantics-driven SMT - Semantic knowledge for Semantics-driven SMT - Applications of multilingual ontology or knowledge bases in semantics- driven SMT - Learning and extracting multilingual semantic knowledge for translation - Semantically motivated evaluation for SMT Submission Instructions ----------------------- We invite authors to submit the following 3 types of papers on topics listed above to the workshop: - Full papers (maximum 8 content pages + 2 pages for references) that report solid and completed work with new experiments, findings and/or approaches. - Short papers (maximum 4 content pages + 2 pages for references) that report - a small, focused contribution - work in progress - a negative result - an interesting application nugget - Opinion papers (2-8 content pages + 2 pages for references) that provide the authors' opinions/thoughts on semantics-driven SMT from the following view angles (but not limited to) - a critical perspective - future directions - summary of past work - comments on current work Submitted papers should be substantially original and unpublished. The reviewing process will be double-blind. Therefore papers must not include authors' names and affiliations. Furthermore, self-references that reveal the authors' identity, e.g., "We previously showed (Smith, 1991) ..." must be avoided. Instead, use citations such as "Smith previously showed (Smith, 1991) ..." Papers that do not conform to these requirements will be rejected without review. In addition, please do not post your submissions on the web until after the review process is complete. Accepted papers will be presented orally or as posters. The decision as to which papers will be presented orally and which as posters will be made by the program committee based on the nature rather than on the quality of the work. Multiple Submission Policy: Papers that have been or will be submitted to other meetings or publications are acceptable, but authors must indicate this information at submission time. If accepted, authors must notify the organizers (dyxiong@suda.edu.cn) as to whether the paper will be presented at the workshop or elsewhere. Submission format: All submissions must be in PDF format and must follow the official ACL 2015 style guidelines which can be found here (http://acl2015.org/call_for_papers.html). Submission website: Please submit your papers at https://www.softconf.com/acl2015/S2MT/ Organizers ---------- Deyi Xiong (Soochow University) Kevin Duh (Nara Institute of Science and Technology) Christian Hardmeier (Uppsala University) Roberto Navigli (Sapienza University of Rome) Programme Committee ------------------- Ondrej Bojar (Charles University) Francis Bond (Nanyang Technological University) Johan Bos (University of Groningen) Rafael E. Banchs (Institute for Infocomm Research) Boxing Chen (National Research Council Canada) Jiajun Chen (Nanjing University) David Chiang (University of Notre Dame) Chris Dyer (Carnegie Mellon University) Spence Green (Stanford University) Kevin Knight (ISI) Alon Lavie (Carnegie Mellon University) Quoc V. Le (Google) Qun Liu (Dublin City University) Shujie Liu (Microsoft Research Asia) Yang Liu (Tsinghua University) Wei Lu (Singapore University of Technology and Design) Preslav Nakov (Qatar Computing Research Institute) Martha Palmer (University of Colorado) Lane Schwartz (University of Illinois) Xiaodong Shi (Xiamen university) Linfeng Song (University of Rochester) Jinsong Su (Xiamen University) Frances Yung (Nara Institute of Science and Technology) Jiajun Zhang (Chinese Academy of Sciences) Yue Zhang (Singapore University of Technology and Design) Tiejun Zhao (Harbin Institute of Technology) Jingbo Zhu (Northeastern University) Will Zou (Stanford University) |
|