Thursday, August 3, 2017, Cypress 1 |
| 9:00-9:05 | Opening |
| 9:05-10:00 | Invited presentation |
| | Users and Data: The Two Neglected Children of Bilingual Natural Language Processing Research
Phillippe Langlais |
| 10:00-10:30 | Session 1: Plagiarism detection |
| | Deep Investigation of Cross-Language Plagiarism Detection Methods
Jérémy Ferrero, Laurent Besacier, Didier Schwab and Frédéric Agnès |
| 10:30-11:00 | Coffee break |
| 11:00-12:00 | Session 2: Sentence alignment and lexicon acquisition |
| | Sentence Alignment using Unfolding Recursive Autoencoders
Jeenu Grover and Pabitra Mitra |
| | Acquisition of Translation Lexicons for Historically Unwritten Languages via Bridging Loanwords
Michael Bloodgood and Benjamin Strauss |
| 12:00-14:00 | Lunch |
| 14:00-15:30 | Session 3: Building comparable corpora |
| | Toward a Comparable Corpus of Latvian, Russian and English Tweets
Dmitrijs Milajevs |
| | Automatic Extraction of Parallel Speech Corpora from Dubbed Movies
Alp Öktem, Mireia Farrús and Leo Wanner |
| | A parallel collection of clinical trials in Portuguese and English
Mariana Neves |
| 15:30-16:00 | Coffee break |
| 16:00-17:40 | Session 4: Shared task session |
| | Overview of the Second BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora
Pierre Zweigenbaum, Serge Sharoff and Reinhard Rapp |
| | Weighted Set-Theoretic Alignment of Comparable Sentences
Andoni Azpeitia, Thierry Etchegoyhen and Eva Martínez Garcia |
| | BUCC 2017 Shared Task: a First Attempt Toward a Deep Learning Framework for Identifying Parallel Sentences in Comparable Corpora
Francis Grégoire and Philippe Langlais |
| | zNLP: Identifying Parallel Sentences in Chinese-English Comparable Corpora
Zheng Zhang and Pierre Zweigenbaum |
| | BUCC2017: A Hybrid Approach for Identifying Parallel Sentences in Comparable Corpora
Sainik Mahata, Dipankar Das and Sivaji Bandyopadhyay |
| 17:40-17:50 | Closing |
