Program of the 15th International Workshop on Spoken Language Translation (IWSLT 2018)
PDF Version of the program you can find here.
We would also like to thank our gold-sponsors:
Monday, October 29, 2018
|
08:30-09:00 |
Workshop Registration and Welcome-Coffee |
|
09:00-09:15 |
Welcome Remarks Marcello Federico, IWSLT 2018 Workshop Chair (FBK/Amazon) |
|
09:15-10:05 |
Invited Speaker Prof. Lucia Specia (Imperial College London & University of Sheffield ) "Multimodal Machine Translation" |
|
10:05-10:20 |
Gold sponsor presentation: Apptek |
|
10:20-10:50 |
Coffee Break |
|
10:50-11:05 |
Silver sponsor presentation: M*Modal |
|
11:05-12:00 |
Overview IWSLT 2018: Overview of the IWSLT 2018 Evaluation Campaign |
|
12:00-13:30 |
Lunch |
|
13:30-15:00 |
Oral Session 1: |
|
13:30-14:00 |
(System description paper) Philip Williams, Marcin Chochowski, Pawel Przybysz, Rico Sennrich, Barry Haddow and Alexandra Birch. Samsung and University of Edinburgh's System for the IWSLT 2018 Low Resource MT Task |
|
14:00-14:30 |
(System description paper) Dan Liu, Junhua Liu, Wu Guo, Shifu Xiong, Zhiqiang Ma, Rui Song, Chongliang Wu and Quan Liu. The USTC-NEL Speech Translation system at IWSLT 2018 |
|
14:30-15:00 |
(Research paper) Viktor Hangya, Fabienne Braune, Yuliya Kalasouskaya and Alexander Fraser. Unsupervised Parallel Sentence Extraction from Comparable Corpora
|
|
15:00-15:30 |
Coffee Break |
|
15:30-17:30 |
Poster Session: |
|
15:30-17:30 |
Papers: • "The JHU/KyotoU Speech Translation System for IWSLT 2018", Hirofumi Inaguma, Xuan Zhang, Zhiqi Wang, Adithya Renduchintala, Shinji Watanabe and Kevin Duh
• “The ADAPT System Description for the IWSLT 2018 Basque to English Translation Task”, Alberto Poncelas, Kepa Sarasola and Andy Way
• “The University of Helsinki submissions to the IWSLT 2018 low-resource translation task” Yves Scherrer
• “Prompsit's Submission to IWSLT 2018 Low Resource Machine Translation Task” Víctor M. Sánchez-Cartagena
• “The AFRL IWSLT 2018 Systems: What Worked, What Didn’t” Brian Ore, Eric Hansen, Katherine Young, Grant Erdmann and Jeremy Gwinnup
• “Alibaba Speech Translation Systems for IWSLT 2018” Fei Huang, Nguyen Bach and Chongjia Ni
• “The MeMAD Submission to the IWSLT 2018 Speech Translation Task” Umut Sulubacak, Aku Rouhe, Jörg Tiedemann, Stig-Arne Grönroos and Mikko Kurimo
• “Neural Speech Translation at AppTek” Evgeny Matusov, Patrick Wilken, Parnia Bahar, Julian Schamper, Pavel Golik, Albert Zeyer, Joan Albert Silvestre-Cerda, Adria Martinez-Villaronga, Hendrik Pesch and Jan-Thorsten Peter
• “KIT’s IWSLT 2018 SLT Translation System” Matthias Sperber, Ngoc Quan Pham, Thai Son Nguyen, Jan Niehues, Markus Müller, Thanh-Le Ha, Sebastian Stüker and Alex Waibel
• “CUNI Basque to English Submission in IWSLT18” Tom Kocmi, Dušan Variš and Ondřej Bojar
• “Adapting Multilingual NMT to Extremely Low Resource Languages, FBK’s Participation of the Basque-English Low Resource MT, IWSLT 2018” Surafel M. Lakew and Marcello Federico
• “The Sogou-TIIC Speech Translation System for IWSLT 2018” Yuguang Wang, Liangliang Shi, Linyu Wei, Weifeng Zhu, Jinkun Chen, Zhichao Wang, Shixue Wen, Wei Chen, Yanfeng Wang and Jia Jia
• “Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018” Mattia Antonino Di Gangi, Roberto Dessì, Roldano Cattoni, Matteo Negri and Marco Turchi
• “Using Spoken Word Posterior Features in Neural Machine Translation” Kaho Osamura, Takatomo Kano, Sakriani Sakti, Katsuhito Sudoh and Satoshi Nakamura
• “Transfer Learning in Multilingual Neural Machine Translation with Dynamic Vocabulary” Surafel Melaku Lakew, Aliia Erofeeva, Matteo Negri, Marcello Federico and Marco Turchi
• "Data Selection with Feature Decay Algorithms Using an Approximated Target Side" Alberto Poncelas, Gideon Maillette de Buy Wenniger and Andy Way |
|
18:30 |
Guided tour through Bruges Start: Grand Hotel Casselbergh – End: De Halve Maan |
| 19:30 |
Dinner in the Brewery “De Halve Maan”, Walplein 26, 8000 Brugge - 15 minutes by taxi - A nice 13-minute walk along the Groenerei |
Tuesday, October 30, 2018
|
09:00-10:00 |
Oral Session 2 |
|
09:00-09:30 |
"Multi-Source Neural Machine Translation with Data Augmentation", Yuta Nishimura, Katsuhito Sudoh, Graham Neubig and Satoshi Nakamura |
|
09:30-10:00 |
"Word Rewarding for Adequate Neural Machine Translation", Yuto Takebayashi, Chenhui Chu, Yuki Arase and Masaaki Nagata |
|
10:00-10:15 |
Gold sponsor Presentation: Amazon |
|
10:15-10:45 |
Coffee break |
|
10:45-12:15 |
Oral Session 3 |
|
10:45-11:15 |
"Analyzing Knowledge Distillation in Neural Machine Translation", Zhang, Josep Crego and Jean Senellart |
|
11:15-11:45 |
"Learning to Segment Inputs for NMT Shows Preference for Character-Level Processing", Julia Kreutzer and Artem Sokolov |
|
11:45-12:15 |
"Machine Translation Human Evaluation: a comprehensive investigation of evaluation based on Post-Editing and its relation with Direct Assessment", Luisa Bentivogli, Mauro Cettolo, Marcello Federico and Christian Federmann |
|
12:15-13:30 |
Lunch |
|
13:30-15:00 |
Oral Session 4 |
|
13:30-14:00 |
"Multiparaphrase Augmentation to Leverage Neural Caption Translation”, Johanes Effendi, Sakriani Sakti, Katsuhito Sudoh and Satoshi Nakamura |
|
14:00-14:30 |
"A Machine Translation Approach for Modernizing Historical Documents Using |
|
14:30-15:00 |
"Word-based Domain Adaptation for Neural Machine Translation", Shen Yan, Shahram Khadivi, Leonard Dahlmann, Pavel Petrushkov and Sanjika Hewavitharana |
| 15:00-15:30 | Coffee Break |
|
15:30-16:45 |
Panel Discussion – the future of machine and speech translation
|
| 16:45-17:00 | Closing and remarks |
In case of any questions, just send an e-mail to Manami Matsuda.
