Monday، March 28، 2011

فوق لیسانس زبانشناسی در آلمان

اول از همه اینکه شما می توانید آخرن اخبار بورسهای اروپا و آمریکا در زمینه پردازش زبان طبیعی را در گروه زیر پیدا کنید.

اما اینبار یک بورس کارشناسی ارشد - فوق لیسانس ـ در آلمان برای زیانشناسی رایانه ای
شروع دوره از سپتامبر ۲۰۱۱ هست و بیشتر برای افرادی که در زمینه زبانشناسی کار کرده اند مناسب است. 

 The University of Zurich is pleased to announce an innovative Master's
 degree program in ?Multilingual Text Analysis - Comparative Corpus
 Linguistics?, beginning in September 2011.
 The Specialized Master in Multilingual Text Analysis is inspired by
 comparative Corpus Linguistics. It combines Linguistics in English,
 German and the Romance languages with methods and techniques from
 Computational Linguistics.

 It has been designed for students who want to complement their interest
 in Linguistics with a qualification in Language Technology. It is also
 suitable for students of Computational Linguistics who want to gain a
 multilingual perspective. Applicants should have a Bachelor degree.

 Comparative Corpus Linguistics is a fast-growing discipline, which is
 partly due to the multitude of translated texts that are now available
 in digitialised form. The demand for interdisciplinary skills in
 languages and computers is increasing, which has created many job
 opportunities. Graduates are well qualified for jobs in translation and
 terminology departments of international companies which manage
 documents in multiple languages, and in the rapidly growing field of
 language technology development.

 Online-Application:
 http://www.uzh.ch/studies/application/master/apply_en.html

 Application Deadline:  April 30, 2011

 For more information about admissions, tuition, and financial
 assistance, please visit the website:
 http://www.mlta.uzh.ch

 Contact Jeannette Roth, Student Counsellor Multilingual Text Analysis:
 m...@cl.uzh.ch

Thursday، August 19، 2010

Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

مجموعه مقالات پنجمین کارگاه ترجمه ماشینی آماری و روشهای ارزیابی ترجمه ماشینی


به تدریح و با خواندن مقالات سعی خواهم کرد خلاصه ای از هر کدام را در زیر همین لیست تکمیل کنم. این مقالات برای کسانی که علاقه مند به کار در زمینه ترجمه ماشینی هستند بسیار مفید خواهد بود چرا که مقایسه ای بین آخرین روشهای ترجمه ماشینی در دنیا انجام شده است. همه سیستمها با یک داده و مکانیزمهای مشابه مورد ارزیابی قرار گرفته اند.

W10-17 [bib]: Entire volume
W10-1700: Front Matter
W10-1701 [bib]: Qin Gao; Nguyen Bach; Stephan Vogel
A Semi-Supervised Word Alignment Algorithm with Partial Manual Alignments
W10-1702 [bib]: Boxing Chen; George Foster; Roland Kuhn
Fast Consensus Hypothesis Regeneration for Machine Translation
W10-1703 [bib]: Chris Callison-Burch; Philipp Koehn; Christof Monz; Kay Peterson; Mark Przybocki; Omar Zaidan
Findings of the 2010 Joint Workshop on Statistical Machine Translation and Metrics for Machine Translation
مقاله بالا گزارشی از ارزیابی کلیه سیستمهای ترجمه ماشینی شرکت کننده در این کارگاه است. علاوه بر این روشهای مختلف ارزیابی ترجمه ماشینی هم ارزیابی شده اند با این هدف که بدانیم کدام روش به ارزیابی انسانی نزذیک تر است.  
 
W10-1704 [bib]: Alexandre Allauzen; Josep M. Crego; \.Ilknur Durgar El-Kahlout; Francois Yvon
LIMSI’s Statistical Translation Systems for WMT’10
W10-1705 [bib]: Ondřej Bojar; Kamil Kos
2010 Failures in English-Czech Phrase-Based MT
W10-1706 [bib]: Cong Hui; Hai Zhao; Bao-Liang Lu; Yan Song
An Empirical Study on Development Set Selection Strategy for Machine Translation Learning
W10-1707 [bib]: Vladimir Eidelman; Chris Dyer; Philip Resnik
The University of Maryland Statistical Machine Translation System for the Fifth Workshop on Machine Translation
W10-1708 [bib]: Christian Federmann; Andreas Eisele; Yu Chen; Sabine Hunsicker; Jia Xu; Hans Uszkoreit
Further Experiments with Shallow Hybrid MT Systems
W10-1709 [bib]: Greg Hanneman; Jonathan Clark; Alon Lavie
Improved Features and Grammar Selection for Syntax-Based MT
W10-1710 [bib]: Christian Hardmeier; Arianna Bisazza; Marcello Federico
FBK at WMT 2010: Word Lattices for Morphological Reduction and Chunk-Based Reordering
W10-1711 [bib]: Carmen Heger; Joern Wuebker; Matthias Huck; Gregor Leusch; Saab Mansour; Daniel Stein; Hermann Ney
The RWTH Aachen Machine Translation System for WMT 2010
W10-1712 [bib]: Carlos A. Henríquez Q.; Marta Ruiz Costa-jussà; Vidas Daudaravicius; Rafael E. Banchs; José B. Mariño
Using Collocation Segmentation to Augment the Phrase Table
W10-1713 [bib]: Stéphane Huet; Julien Bourdaillet; Alexandre Patry; Philippe Langlais
The RALI Machine Translation System for WMT 2010
W10-1714 [bib]: Michael Jellinghaus; Alexandros Poulis; David Kolovratník
Exodus - Exploring SMT for EU Institutions
W10-1715 [bib]: Philipp Koehn; Barry Haddow; Philip Williams; Hieu Hoang
More Linguistic Annotation for Statistical Machine Translation
W10-1716 [bib]: Patrik Lambert; Sadaf Abdul-Rauf; Holger Schwenk
LIUM SMT Machine Translation System for WMT 2010
W10-1717 [bib]: Samuel Larkin; Boxing Chen; George Foster; Ulrich Germann; Eric Joanis; Howard Johnson; Roland Kuhn
Lessons from NRC’s Portage System at WMT 2010
W10-1718 [bib]: Zhifei Li; Chris Callison-Burch; Chris Dyer; Juri Ganitkevitch; Ann Irvine; Sanjeev Khudanpur; Lane Schwartz; Wren Thornton; Ziyuan Wang; Jonathan Weese; Omar Zaidan
Joshua 2.0: A Toolkit for Parsing-Based Machine Translation with Syntax, Semirings, Discriminative Training and Other Goodies
W10-1719 [bib]: Jan Niehues; Teresa Herrmann; Mohammed Mediani; Alex Waibel
The Karlsruhe Institute for Technology Translation System for the ACL-WMT 2010
W10-1720 [bib]: Sergio Penkale; Rejwanul Haque; Sandipan Dandapat; Pratyush Banerjee; Ankit K. Srivastava; Jinhua Du; Pavel Pecina; Sudip Kumar Naskar; Mikel L. Forcada; Andy Way
MATREX: The DCU MT System for WMT 2010
W10-1721 [bib]: Aaron Phillips
The Cunei Machine Translation Platform for WMT ’10
W10-1722 [bib]: Juan Pino; Gonzalo Iglesias; Adrià de Gispert; Graeme Blackwood; Jamie Brunning; William Byrne
The CUED HiFST System for the WMT10 Translation Shared Task
W10-1723 [bib]: Marion Potet; Laurent Besacier; Hervé Blanchon
The LIG Machine Translation System for WMT 2010
W10-1724 [bib]: Markus Saers; Joakim Nivre; Dekai Wu
Linear Inversion Transduction Grammar Alignments as a Second Translation Path
W10-1725 [bib]: Germán Sanchis-Trilles; Jesús Andrés-Ferrer; Guillem Gascó; Jesús González-Rubio; Pascual Martínez-Gómez; Martha-Alicia Rocha; Joan-Andreu Sánchez; Francisco Casacuberta
UPV-PRHLT English–Spanish System for WMT10
W10-1726 [bib]: Lane Schwartz
Reproducible Results in Parsing-Based Machine Translation: The JHU Shared Task Submission
W10-1727 [bib]: Sara Stymne; Maria Holmqvist; Lars Ahrenberg
Vs and OOVs: Two Problems for Translation between German and English
W10-1728 [bib]: Jörg Tiedemann
To Cache or Not To Cache? Experiments with Adaptive Models in Statistical Machine Translation
W10-1729 [bib]: Sami Virpioja; Jaakko Väyrynen; Andre Mansikkaniemi; Mikko Kurimo
Applying Morphological Decompositions to Statistical Machine Translation
W10-1730 [bib]: Zdeněk Žabokrtský; Martin Popel; David Mareček
Maximum Entropy Translation Model in Dependency-Based MT Framework
W10-1731 [bib]: Francisco Zamora-Martinez; Germán Sanchis-Trilles
UCH-UPV English–Spanish System for WMT10
W10-1732 [bib]: Daniel Zeman
Hierarchical Phrase-Based MT at the Charles University for the WMT 2010 Shared Task
W10-1733 [bib]: Baskaran Sankaran; Ajeet Grewal; Anoop Sarkar
Incremental Decoding for Phrase-Based Statistical Machine Translation
W10-1734 [bib]: Fabienne Fritzinger; Alexander Fraser
How to Avoid Burning Ducks: Combining Linguistic Analysis and Corpus Statistics for German Compound Processing
W10-1735 [bib]: Arianna Bisazza; Marcello Federico
Chunk-Based Verb Reordering in VSO Sentences for Arabic-English Statistical Machine Translation
W10-1736 [bib]: Hideki Isozaki; Katsuhito Sudoh; Hajime Tsukada; Kevin Duh
Head Finalization: A Simple Reordering Rule for SOV Languages
W10-1737 [bib]: Ronan Le Nagard; Philipp Koehn
Aiding Pronoun Translation with Co-Reference Resolution
W10-1738 [bib]: David Vilar; Daniel Stein; Matthias Huck; Hermann Ney
Jane: Open Source Hierarchical Translation, Extended with Reordering and Lexicon Models
W10-1739 [bib]: Loïc Barrault
MANY: Open Source MT System Combination at WMT’10
W10-1740 [bib]: Ergun Bicici; S. Serdar Kozat
Adaptive Model Weighting and Transductive Regression for Predicting Best System Combinations
W10-1741 [bib]: Ergun Bicici; Deniz Yuret
L1 Regularized Regression for Reranking and System Combination in Machine Translation
W10-1742 [bib]: Jinhua Du; Pavel Pecina; Andy Way
An Augmented Three-Pass System Combination Framework: DCU Combination System for WMT 2010
W10-1743 [bib]: Jesús González-Rubio; Germán Sanchis-Trilles; Joan-Andreu Sánchez; Jesús Andrés-Ferrer; Guillem Gascó; Pascual Martínez-Gómez; Martha-Alicia Rocha; Francisco Casacuberta
The UPV-PRHLT Combination System for WMT 2010
W10-1744 [bib]: Kenneth Heafield; Alon Lavie
CMU Multi-Engine Machine Translation for WMT 2010
W10-1745 [bib]: Almut Silja Hildebrand; Stephan Vogel
CMU System Combination via Hypothesis Selection for WMT’10
W10-1746 [bib]: Sushant Narsale
JHU System Combination Scheme for WMT 2010
W10-1747 [bib]: Gregor Leusch; Hermann Ney
The RWTH System Combination System for WMT 2010
W10-1748 [bib]: Antti-Veikko Rosti; Bing Zhang; Spyros Matsoukas; Richard Schwartz
BBN System Description for WMT10 System Combination Task
W10-1749 [bib]: Alexandra Birch; Miles Osborne
LRscore for Evaluating Lexical and Reordering Quality in MT
W10-1750 [bib]: Elisabet Comelles; Jesus Gimenez; Lluis Marquez; Irene Castellon; Victoria Arranz
Document-Level Automatic MT Evaluation based on Discourse Representations
W10-1751 [bib]: Michael Denkowski; Alon Lavie
METEOR-NEXT and the METEOR Paraphrase Tables: Improved Evaluation Support for Five Target Languages
W10-1752 [bib]: Marcus Dobrinkat; Tero Tapiovaara; Jaakko Väyrynen; Kimmo Kettunen
Normalized Compression Distance Based Measures for MetricsMATR 2010
W10-1753 [bib]: Yifan He; Jinhua Du; Andy Way; Josef van Genabith
The DCU Dependency-Based Metric in WMT-MetricsMATR 2010
W10-1754 [bib]: Chang Liu; Daniel Dahlmeier; Hwee Tou Ng
TESLA: Translation Evaluation of Sentences with Linear-Programming-Based Analysis
W10-1755 [bib]: Billy Wong; Chunyu Kit
The Parameter-Optimized ATEC Metric for MT Evaluation
W10-1756 [bib]: Abhishek Arun; Barry Haddow; Philipp Koehn
A Unified Approach to Minimum Risk Training and Decoding
W10-1757 [bib]: Kevin Duh; Katsuhito Sudoh; Hajime Tsukada; Hideki Isozaki; Masaaki Nagata
N-Best Reranking by Multitask Learning
W10-1758 [bib]: Ralf Brown
Taming Structured Perceptrons on Wild Feature Vectors
W10-1759 [bib]: Kashif Shah; Loïc Barrault; Holger Schwenk
Translation Model Adaptation by Resampling
W10-1760 [bib]: Michael Paul; Andrew Finch; Eiichiro Sumita
Integration of Multiple Bilingually-Learned Segmentation Schemes into Statistical Machine Translation
W10-1761 [bib]: Hieu Hoang; Philipp Koehn
Improved Translation with Source Syntax Labels
W10-1762 [bib]: Katsuhito Sudoh; Kevin Duh; Hajime Tsukada; Tsutomu Hirao; Masaaki Nagata
Divide and Translate: Improving Long Distance Reordering in Statistical Machine Translation
W10-1763 [bib]: Rabih Zbib; Spyros Matsoukas; Richard Schwartz; John Makhoul
Decision Trees for Lexical Smoothing in Statistical Machine Translation

Monday، June 07، 2010

یک بورس دکترا و دو فوق دکترا در زمینه ترجمه ماشینی - فرانسه

The computer science laboratory of the University of Le Mans (LIUM) has openings for two postdoc and one PhD position in the field of statistical machine translation.

LIUM performs research in statistical machine translation since several years and we are particularly interested in new machine learning methods. Ongoing work includes continuous space language and translation models, unsupervised training, comparable corpora, translation model adaptation, domain specific models, integration of linguistic knowledge, etc.

LIUM is involved in several international projects, in particular EuromatrixPlus, Gale and several French national projects (e.g. http://www.cosmat.fr). We have very successfully participated in several international evaluations, in particular NIST'09 or WMT'10. A large computer cluster is available to support the research.

The postdoc positions are immediately available and the PhD will start in October 2010. Competitive salaries are available. Postdoc candidates must have a proven experience in machine learning, NLP and SMT, ideally with the Moses decoder. We are very actively working on large systems to translate from Arabic and Chinese and we are therefore interested in a postdoc with knowledge in one of those languages.

Le Mans is located in between Paris and the Atlantic ocean. Both can be reached in about 1 hour by high speed train. The Loire valley with many wineries and other attractions is just a short drive away ...

For information, please contact Holger Schwenk by email: Holger.Schwenk@lium.univ-lemans.fr