Home | Legals | Data Protection | Sitemap | KIT


Program of the 16th International Workshop on Spoken Language Translation (IWSLT 2019)

PDF Version of the program you can find here.


Saturday, November 2, 2019



Workshop Registration and Welcome-Coffee


Welcome Remarks

Dekai Wu, IWSLT 2019 Workshop Chair (HKUST)


Overview IWSLT 2019:

Overview of the IWSLT 2019 Loic Barrault, Roldano Cattoni, Thanh-Le Ha, Matteo Negri, Jan Niehues, Elizabeth Salesky, Ramon Sanabria, Lucia Specia, Sebastian Stüker, Marco Turchi Evaluation Campaign


Coffee Break   


Oral Session 1:


Qiao Cheng, Meiyuan Fang, Yaqian Han, Jin Huang and Yitao Duan.

Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training


Yingbo Gao, Christian Herold, Weiyue Wang and Hermann Ney.

Exploring Kernel Functions in the Softmax Layer for Contextual Word Classification


Pierre Godard, Laurent Besacier and François Yvon.

Controlling Utterance Length in NMT-based Word Segmentation with Attention


Toan Q. Nguyen and Julian Salazar.

Transformers without Tears: Improving the Normalization of Self-Attention




Poster Session 1

System Papers

Mattia A. Di Gangi, Matteo Negri, Viet Nhat Nguyen, Amirhossein Tebbifakhr, Marco Turchi. Data Augmentation for End-to-End Speech Translation: FBK@IWSLT ’19#

Felix Schneider, Alex Waibel. KIT’s Submission to the IWSLT 2019 Shared Task on Text Translation

Tomasz Potapczyk, Pawel Przybysz, Marcin Chochowski, Artur Szumaczuk. Samsung’s System for the IWSLT 2019 End-to-End Speech Translation Task

Loïc Vial Benjamin Lecouteux Didier Schwab Hang Le Laurent Besacier. The LIG system for the English-Czech Text Translation Task of IWSLT 2019

Tejas Srinivasan, Ramon Sanabria, Florian Metze. CMU’s Machine Translation System for IWSLT 2019

Joanna Wetesko, Marcin Chochowski, Pawel Przybysz, Philip Williams, Roman Grundkiewicz, Rico Sennrich, Barry Haddow, Antonio Valerio Miceli Barone, Alexandra Birch. Samsung and University of Edinburgh’s System for the IWSLT 2019

Martin Popel, Christian Federmann. Domain Adaptation of Document-Level NMT in IWSLT19

Mei Tu, Wei Liu, Lijie Wang, Xiao Chen, Xue Wen. End-to-end Speech Translation System Description of LIT for IWSLT 2019

Zixiu Wu, Ozan Caglayan, Julia Ive, Josiah Wang, Lucia Specia. Transformer-based Cascaded Multimodal Speech Translation

Ha Nguyen, Natalia Tomashenko, Marcely Zanon Boito, Antoine Caubrière, Fethi Bougares, Mickael Rouvier, Laurent Besacier, Yannick Estève. ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task

Hirofumi Inaguma, Shun Kiyono, Nelson Enrique Yalta Soplin, Jun Suzuki, Kevin Duh, Shinji Watanabe. ESPnet How2 Speech Translation System for IWSLT 2019: Pre-training, Knowledge Distillation, and Going Deeper

Ngoc-Quan Pham, Thai-Son Nguyen, Thanh-Le Ha, Juan Hussain, Felix Schneider, Jan Niehues, Sebastian Stüker, Alexander Waibel. The IWSLT 2019 KIT Speech Translation System

Xiaopu Li, Zhengshan Xue, Jie Hao. OPPO NMT System for IWSLT 2019


Coffee Break


Oral Session 2:


Carolina Scarton, Mikel Forcada, Miquel Esplà and Lucia Specia.

Estimating post-editing effort: a study on human judgements, task-based and reference-based metrics of MT quality


Mattia di Gangi, Robert Enyedi, Alessandra Brusadin and Marcello Federico.

Robust Neural Machine Translation for Clean and Noisy Speech Transcripts


Jitao Xu, Josep Crego and Jean Senellart.

Lexical Micro-adaptation for Neural Machine Translation


Minhquang Pham, Josep Crego, François Yvon and Jean Senellart.

Generic and Specialized Word Embeddings for Multi-Domain Machine Translation


End of 1st day


Sunday, November 3, 2019



Oral Session 3


Valentin Macé and Christophe Servan. Using Whole Document Context in Neural Machine Translation

Using Whole Document Context in Neural Machine Translation


Juan Pino, Liezl Puzon, Jiatao Gu, Xutai Ma, Arya McCarthy and Deepak Gopinath.

Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade


Coffee Break


Poster Session 2:

Tejas Srinivasan, Ramon Sanabria and Florian Metze.

Multitask Learning For Different Subword Segmentations In Neural Machine Translation


Jan Rosendahl, Viet Anh Khoa Tran, Weiyue Wang and Hermann Ney.

Analysis of Positional Encodings for Neural Machine Translation


Philipp Wiesenbach and Stefan Riezler.

Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs


Surafel Lakew, Mattia di Gangi and Marcello Federico.

Controlling the Output Length of Neural Machine Translation


Anh Khoa Ngo Ho and François Yvon.

Neural Baselines for Word Alignment


Surafel Melaku Lakew, Alina Karakanta, Matteo Negri, Marcello Federico and Marco Turchi.

Adapting Multilingual Neural Machine Translation to Unseen Languages


Parnia Bahar, Albert Zeyer, Ralf Schlüter and Hermann Ney.

On Using SpecAugment for End-to-End Speech Translation


Thi-Vinh Ngo, Thanh-Le Ha, Phuong-Thai Nguyen and Le-Minh Nguyen.

How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation Systems


Yuchen Yan and Dekai Wu.

Efficient Bilingual Generalization from Neural Transduction Grammar Induction





Panel discussion on the future of IWSLT

15:00-15:15  Closing and remarks


In case of any questions, just send an e-mail to Margit Rödder.