Official website for the workshop can be accessed via the link https://sites.google.com/site/wptp2012/

Post-Editing (PE) is possibly the oldest form of human-machine cooperation for translation, having been around for just about as long as operational MT systems. Recently however, there seems to be a surge of interest for PE among the wider user community, partly due to the increasing quality of MT output, but also to the availability of free, high-quality software.

Yet, the success of a PE operation depends on many more factors than just software, and for every PE success story, probably many more failures go unreported. This workshop will be a chance for PE researchers and practitioners to get together and openly discuss the weaknesses and strengths of existing technology, to properly and objectively assess PE effectiveness, to establish better practices, and propose tools and technological PE solutions that are built around the real needs of users.

This one-day workshop will be held during the next AMTA Meeting, which is taking place in San Diego CA, October 28 to November 1, 2012. The workshop will consist of oral presentations of original work and a short demo session.

Topics of interest:

We invite original papers on the following topics, but also welcome other ideas which touch on potential fruitful human-machine collaborations for translation.

• Best practices for PE
• Post-editing machine translation vs. Post-editing translation memories vs. Revising real (human) translations
• Training for post-editing
• Managing the transition from TM to TM+MT or just MT
• PE evaluation methodology and metrics
• Collecting and sharing PE data
• Innovative uses of post-editor feedback
• Real-time adaptation / Online learning / Incremental SMT training / Automatic post-editing
• Prediction of PE effort
• Confidence estimation / Error-detection for PE
• PE UI design and innovative functionalities
• Integration of MT within computer-assisted translation (CAT) environments
• Reducing post-editing effort through pre-processing techniques

We also invite one-page descriptions of interesting tools related to post-editing, including commercial products, in-house systems and open source software. Authors should be ready to present demos of the tools during the workshop. See Demo submission instructions below.

Important dates:

• Submission deadline: Friday, August 10
• Notifications of acceptance: Friday, August 31
• Final "camera-ready" versions: Friday, September 7

Workshop Organizers

• Sharon O'Brien -- CNGL / DCU
• Michel Simard -- National Research Council Canada
• Lucia Specia -- University of Sheffield

Program Committee

• Nora Aranberri -- TAUS
• Diego Bartolome -- tauyou
• Louise Brunette -- Université du Québec en Outaouais
• Michael Carl -- Copenhagen Business School
• Francisco Casacuberta -- Universitat Politècnica de València
• Mike Dillinger -- Translation Optimization Partners
• Stephen Doherty -- Dublin City University
• Andreas Eisele -- European Commission
• Jakob Elming -- Copenhagen Business School
• Atefeh Farzindar -- NLP Technologies
• Marcello Federico -- FBK-IRST
• Mikel L. Forcada -- Universitat d’Alacant
• Ana Guerberof -- Logoscript
• Nizar Habash -- Columbia University
• Daniel Hardt -- Copenhagen Business School
• Kristian Tangsgaard Hvelplund -- Copenhagen Business School
• Pierre Isabelle -- National Research Council Canada
• Maxim Khalilov -- TAUS
• Philipp Koehn -- University of Edinburgh
• Roland Kuhn -- National Research Council Canada
• Philippe Langlais -- RALI / Université de Montréal
• Alon Lavie -- Carnegie Mellon University
• Elliott Macklovitch -- Translation Bureau Canada
• Daniel Marcu -- SDL / USC / ISI
• John Moran -- Centre for Next Generation Localization
• Kristen Parton -- Columbia University
• Maja Popovic -- DFKI
• Alexandros Poulis -- European Parliament / Intrasoft
• Johann Roturier -- Symantec
• Jean Senellart -- SYSTRAN
• Myriam Siftar -- MTM LinguaSoft
• Roberto Silva -- Celer Soluciones
• Radu Soricut -- SDL International
• Midori Tatsumi -- Dublin City University
• Jörg Tiedemann -- Uppsala University
• Andy Way -- Applied Language Solutions
• Chris Wendt -- Microsoft Research

The workshop on Translation and Social Media (TSM 2012) has been cancelled.

Download Workshop program : program-CAASL4

Three years after CAASL3, this workshop provides an opportunity for developers and researchers in Academia, the industry, and government to present their work, exchange ideas, and demonstrate systems that focus on the challenging task of dealing with all aspects in natural language processing for languages that use the Arabic script. It also provides an opportunity to assess the progress that has been made since the third workshop in 2009. Authors are invited to submit papers on completed original research and research in progress on any aspect of NLP for the Arabic Script-based languages.

Papers should relate directly or indirectly to the following themes:

• Statistical and rule-based machine translation
• Translation Aids
• Evaluation Methods and Techniques of Machine Translation systems
• Localization and multilingual information retrieval systems
• Shallow and deep parsing
• Data driven approaches
• Entity extraction
• Tokenization and segmentation
• Name matching
• Speech synthesis and recognition
• Text to speech systems
• Semantic analysis
• Knowledge Bases
• Information retrieval
• Semantic web and inferences
• Topic Detection and text summarization.

Workshop Chair

• Ali Farghaly

Program Chair

• Farhard Oroumchian

Workshop Dates and Deadlines

• The workshop will be held on Thursday November 1st, 2012 from 9 to 5.
• Papers submission deadline: August 8th, 2012
• Author notification: August 15, 2012
• Camera Ready submissions due: September 7, 2012
• Website for submission: https://www.softconf.com/amta2012/CAASL4/
• Contact Information: alifarghaly@yahoo.com

Organizing Committee: Ali Farghaly and Farhard Oroumchian

Tentative Program Committee

• Tim Buckwalter -- University of Maryland, USA
• Violetta Cavalli-Sforza -- AlAkhawayn University, Moroccoa
• Sherri Condon -- MITRE, USA
• Aly Fahmy -- Cairo University
• Mona Diab -- Columbia University, USA
• Joseph Dichy -- Lyon University, France
• Andrew Freeman -- University of Washington, USA
• Nizar Habash -- Columbia University, USA
• Lamia Hadrich Belguith -- University of Sfax, Tunisia
• Sarmad Hussain -- CRULP, Pakistan
• Mohamed Maamouri -- Linguistics Data Consortium, USA
• Farhad Oroumchian -- University of Wollongong in Dubai, United Arab Emirates
• Jean Sennellart -- SYSTRAN, France
• Khaled Shaalan -- The British University in Dubai, United Arab Emirates
• Ahmed Rafea -- The American University in Cairo, Egypt
• Imed Zitouni -- IBM, USA
• Azadeh Shakery -- University of Tehran, Iran
• Karim Bouzoubaa -- Mohamed Vth Agdal University, Morocco
• Abdelhadi Saudi -- École Nationale de l'Industrie Minérale, Morocco

Workshop Website: http://computing.dcu.ie/~tokita/MONOMT/monomt.htm

Invited Speakers

• Marcello Federico (FBK, Italy)
• George Foster (National Research Council Canada, Canada)
• Philipp Koehn (University of Edinburgh, UK)
• Qun Liu (Dublin City University, Ireland & Chinese Academy of Science, China)
• Evgeny Matusov (SAIC)
• Taro Watanabe (NICT, Japan)
• (More to come)

Description

Due to the increasing demands for high quality translation, monolingual Machine Translation (MT) subtasks are frequently encountered in various occasions, where one MT task is decomposed into several subtasks some of which can be called `monolingual'. Such monolingual MT subtasks include:

1. MT for morphologically rich languages, [Bojar, 08] aimed at dealing with morphologic richness of the target, as is the case with the English-Czech (EN-CZ) language pair. An MT task is thus split into two subtasks: first, English is (`bilingually') translated into simplified Czech and then, the obtained morphologically normalized Czech is (`monolingually') translated into morphologically rich Czech;
2. system combination [Matusov et al., 05], where a source sentence is first translated into the target language by several MT systems, and then, the obtained translations are combined to create / generate the output in the same language;
3. statistical post-editing [Dugast et al., 07; Simard et al., 07], where a source sentence is first translated into the target language by a rule-based MT system and then, the obtained output is `monolingually' translated by an SMT system;
4. domain adaptation using transfer learning [Daume III, 07]: the source side written in a `source' domain (e.g., newswires) is converted into the target side written in a `target' domain (e.g., patents);
5. transliteration between phonemes / alphabets [Knight and Graehl, 98];
6. considering reordering issues (SVO and SOV) [Katz-Brown et al., 11];
7. MERT process [Arun et al., 10];
8. translation memory (TM) and MT integration [Ma et al., 11];
9. paraphrasing for creating additional training data or for evaluation purposes.
10. (error identification and voting with independent monolingual crowdsources [Hu et al., 11]).

A distinction could be established between bilingual MT tools (B-tools) and monolingual MT tools (M-tools) that may be exploited for monolingual MT. Consider, e.g., monolingual subtasks such as MT for morphologically rich languages, statistical post-editing, or transliteration and a task of system combination or domain adaptation as respective representatives. The latter group is often approached with monolingual M-tools like monolingual word alignment [Matusov et al., 05; He et al., 08] and the minimization of Bayes risk [Kumar and Byrne, 02] (on the outputs of combined systems). However, the former usually employs bilingual MT tools, like GIZA++ [Och and Ney, 04] to extract bilingual phrases and MAP decoding on them. The way M-tools and B-tools are used for monolingual MT is an issue of particular interest for this workshop.

This workshop is intended to provide the opportunity to discuss ideas and share opinions on the question of the applicability of M-tools or B-tools for monolingual MT subtasks, and on their respective strengths and weaknesses in specific settings. Furthermore we wish to provide opportunity to demonstrate successful usecases of M-tools.

Possible questions, that are encouraged to be addressed during the workshop, include:

• ways of applying M-tools to monolingual MT subtasks such as MT for morphologically rich languages and statistical post-editing.
• investigation of the suitability of B-tools or M-tools for monolingual MT subtasks.
• performance improvements of monolingual word alignment tools, since these are necessary for specific monolingual subtasks, such as MT for morphologically rich languages and statistical post-editing.

Important Dates

• Submission deadline: August 14, 2012
• Notification to authors: August 31, 2012
• Camera ready: September 6, 2012
• Workshop: November 1, 2012

Topics of Interest

Original papers are invited on different aspects of monolingual MT, such as:

• MT for morphologically rich languages
• System combination
• Statistical post-editing
• Domain adaptation
• MERT process
• MT for reordering mismatched language pairs (SVO and SOV, ...)
• MT-TM integration (i.e. MT systems whose prior knowledge includes bilingual terminology and TM)
• Transliteration
• MT using textual entailment
• MT using confidence estimation
• Paraphrasing
• Hybrid MT

Papers describing the mechanism of MT tools that may be considered 'monolingual' are also encouraged. Some possible topics are listed below:

• MBR decoding, consensus decoding
• Monolingual word alignment (based on TER, METEOR,...)
• Language models constructed by learning the representation of data
• Data structure related matters
• Ranking algorithms
• Multitask learning (in the context of domain adaptation)

Organizers

• Tsuyoshi Okita (Dublin City University, Ireland)
• Artem Sokolov (LIMSI, France)
• Taro Watanabe (National Institute of Information and Communications Technology, Japan)

Program Committee (Tentative)

• Bogdan Babych (University of Leeds, UK)
• Loic Barrault (LIUM, Universite du Maine, France)
• Nicola Bertoldi (FBK, Italy)
• Ergun Bicici (CNGL, Dublin City University, Ireland)
• Boxing Chen (NRC Institute for Information Technology, Canada)
• Trevor Cohn (University of Sheffield, UK)
• Marta Ruiz Costa-jussa (Barcelona Media, Spain)
• Josep M. Crego (SYSTRAN, France)
• John DeNero (Google, USA)
• Jinhua Du (Xi'an University of Technology, China)
• Kevin Duh (Nara Institute of Science and Technology, Japan)
• Chris Dyer (CMU, USA)
• Christian Federmann (DFKI, Germany)
• Yvette Graham (Dublin City University, Ireland)
• Barry Haddow (University of Edinburgh, UK)
• Xiadong He (Microsoft, USA)
• Jagadeesh Jagarlamudi (University of Maryland, USA)
• Jie Jiang (Applied Language Solutions, UK)
• Philipp Koehn (University of Edinburgh, UK)
• Shankar Kumar (Google, USA)
• Alon Lavie (CMU, USA)
• Yanjun Ma (Baidu, China)
• Aurelien Max (LIMSI, University Paris Sud, France)
• Maite Melero (Barcelona Media, Spain)
• Philip Resnik (University of Maryland, USA)
• Stefan Riezler (University of Heidelberg, Germany)
• Lucia Specia (University of Sheffield, UK)
• Marco Turchi (JRC, Italy)
• Antal van den Bosch (Radboud University Nijmegen, Netherlands)
• Xianchao Wu (Baidu, Japan)
• Dekai Wu (HKUST, Honkong)
• Francois Yvon (LIMSI, University Paris Sud, France)
• more...

Contact

• Email : tokita@computing.dcu.ie