| 08:55-9:00 |
Opening Remarks |
| |
|
| |
Session 1: Invited Presentation |
| 09:00-10:00 |
Kyo Kageura |
| |
Cross-lingual Correspondences of Terms in Texts and Terminologies: Theoretical Issues and Practical Implications |
| |
|
| |
Session 2a: Applications of Comparable Corpora |
| 10:00-10:30 |
Laurent Prévot, Matthieu Stali and Shu-Chuan Tseng |
| |
Grouping conversational markers across languages by exploiting large comparable corpora and unsupervised segmentation |
| 10:30-11:00 |
Coffee Break |
| |
|
| |
Session 2b: Applications of Comparable Corpora |
| 11:00-11:30 |
Bartholomäus Wloka |
| |
Identifying Bilingual Topics in Wikipedia for Efficient Parallel Corpus Extraction and Building Domain-Specific Glossaries for the Japanese-English Language Pair |
| 11:30-12:00 |
Firas Sabbah and Ahmet Aker |
| |
Creating Comparable Corpora through Topic Mappings |
| 12:00-12:30 |
Pierre Lison and A. Seza Dogruöz |
| |
Detecting Machine-translated Subtitles in Large Parallel Corpora |
| 12:30-14:00 |
Lunch Break |
| |
|
| |
Session 3: Invited Presentation |
| 14:00-15:00 |
Yves Lepage |
| |
Quasi-Parallel Corpora: Hallucinating Translations for the Chinese-Japanese Language Pair |
| |
|
| |
Session 4a: Shared Task: Parallel Sentence Extraction |
| 15:00-15:30 |
Pierre Zweigenbaum, Serge Sharoff and Reinhard Rapp |
| |
Overview of the Third BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora |
| 15:30-16:00 |
Houda Bouamor and Hassan Sajjad |
| |
H2@BUCC18: Parallel Sentence Extraction from Comparable Corpora Using Multilingual Sentence Embeddings |
| 16:00-16:30 |
Coffee Break |
| |
|
| |
Session 4b: Shared Task: Parallel Sentence Extraction |
| 16:30-17:00 |
Andoni Azpeitia, Thierry Etchegoyhen and Eva Martinez Garcia |
| |
Extracting Parallel Sentences from Comparable Corpora with STACC Variants |
| 17:00-17:30 |
Chongman Leong, Derek F. Wong and Lidia S. Chao |
| |
UM-pAligner: Neural Network-Based Parallel Sentence Identification Model |
| 17:30-17:35 |
Closing |
| |
|
