ACL Workshop on Building and Using Parallel Texts


Wednesday, June 29, 2005

 Invited Talk
9:00--10:00Mike Maxwell So many languages, so few resources: How to bridge the gap?
 Session 1: Long Papers
10:00--10:20Association-Based Bilingual Word Alignment
Robert C. Moore
 Session 2: Long Papers (continued)
11:00--11:20Cross Language Text Categorization by Acquiring Multilingual Domain Models from Comparable Corpora
Alfio Gliozzo and Carlo Strapparava
11:20--11:40Parsing Word-Aligned Parallel Corpora in a Grammar Induction Context
Jonas Kuhn
11:40--12:00Bilingual Word Spectral Clustering for Statistical Machine Translation
Bing Zhao, Eric P. Xing and Alex Waibel
12:00--12:20Revealing Phonological Similarities between Related Languages from Automatically Generated Parallel Corpora
Karin Müller
12:20--12:40Augmenting a Small Parallel Text with Morpho-Syntactic Language
Maja Popović, David Vilar, Hermann Ney, Slobodan Jovicić and Zoran Sarić
 Session 3: Long Papers (continued)
2:00--2:20Induction of Fine-Grained Part-of-Speech Taggers via Classifier Combination and Crosslingual Projection
Elliott Drábek and David Yarowsky
2:20--2:40A Hybrid Approach to Align Sentences and Words in English-Hindi Parallel Corpora
Niraj Aswani and Robert Gaizauskas
 Shared Task I Overview
2:40--3:00Word Alignment for Languages with Scarce Resources
Joel Martin, Rada Mihalcea and Ted Pedersen
 Session 4: Shared Task I Papers
3:00--3:15NUKTI: English-Inuktitut Word Alignment System Description
Philippe Langlais, Fabrizio Gotti and Guihong Cao
3:15--3:30Models for Inuktitut-English Word Alignment
Charles Schafer and Elliott Drábek
 Session 5: Shared Task I Papers (continued)
4:00--4:15Improved HMM Alignment Models for Languages with Scarce Resources
Adam Lopez and Philip Resnik
4:15--4:30Symmetric Probabilistic Alignment
Ralf D. Brown, Jae Dong Kim, Peter J. Jansen and Jaime G. Carbonell
4:30--4:45ISI's Participation in the Romanian-English Alignment Task
Alexander Fraser and Daniel Marcu
4:45--5:00Experiments Using MAR for Aligning Corpora
Juan Miguel Vilar
 Shared Task I Papers without Presentations
 Comparison, Selection and Use of Sentence Alignment Algorithms for New Language Pairs
Anil Kumar Singh and Samar Husain
 Combined Word Alignments
Tufis Dan, Ion Radu, Ceausu Alexandru and Stefanescu Dan
 LIHLA: Shared Task System Description
Helena M. Caseli, Maria G. V. Nunes and Mikel L. Forcada
 Aligning words in English-Hindi Parallel Corpora
Niraj Aswani and Robert Gaizauskas
 Shared Task I Panel Discussion
5:00--6:00TBA Lessons Learned, and Future Directions

Thrusday, June 30, 2005

 Shared Task II Overview
9:15--9:30Shared Task: Statistical Machine Translation between European Languages
Philipp Koehn and Christof Monz
 Session 6: Shared Task II Papers
9:30--9:45Improved Language Modeling for Statistical Machine Translation
Katrin Kirchhoff and Mei Yang
9:45--10:00PORTAGE: A Phrase-Based Machine Translation System
Fatiha Sadat, Howard Johnson, Akakpo Agbago, George Foster, Roland Kuhn, Joel Martin and Aaron Tikuisis
10:00--10:15Statistical Machine Translation of Euparl Data by using Bilingual N-grams
Rafael E. Banchs, Josep M. Crego, Adrià de Gispert, Patrik Lambert and José B. Mariño
 Session 7: Shared Task II Papers (continued)
11:00--11:15RALI: SMT Shared Task System Description
Philippe Langlais, Guihong Cao and Fabrizio Gotti
11:15--11:30A Generalized Alignment-Free Phrase Extraction
Bing Zhao and Stephan Vogel
11:30--11:45Combining Linguistic Data Views for Phrase-based SMT
Jesús Giménez and Lluís Màrquez
11:45--12:00Improving Phrase-Based Statistical Translation by Modifying Phrase Extraction and Including Several Features
Marta Ruiz Costa-jussà and José A. R. Fonollosa
12:00--12:15First Steps towards Multi-Engine Machine Translation
Andreas Eisele
12:15--12:30Competetive Grouping in Integrated Phrase Segmentation and Alignment Model
Ying Zhang and Stephan Vogel
 Shared Task II Paper without Presentation
 Deploying Part-of-Speech Patterns to Enhance Statistical Phrase-Based Machine Translation Resources
Christina Lioma and Iadh Ounis
 Invited Talk
2:00--3:00Franz Och Statistical Machine Translation: The Fabulous Present and Future
 Session 7: Long Papers
3:10--3:30Novel Reordering Approaches in Phrase-Based Statistical Machine Translation
Stephan Kanthak, David Vilar, Evgeny Matusov, Richard Zens and Hermann Ney
 Session 8: Long Papers (continued)
4:00--4:20Gaming Fluency: Evaluating the Bounds and Expectations of Segment-based Translation Memory
John Henderson and William Morgan
4:20--4:40Hybrid Example-Based SMT: the Best of Both Worlds?
Declan Groves and Andy Way
4:40--5:00Word Graphs for Statistical Machine Translation
Richard Zens and Hermann Ney
5:00--5:20A Recursive Statistical Translation Model
Juan Miguel Vilar and Enrique Vidal
5:20--5:40Training and Evaluating Error Minimization Decision Rules for Statistical Machine Translation
Ashish Venugopal, Andreas Zollmann and Alex Waibel