Program
Program
Note: Zoom links are available on the ACL 2022 virtual site (after registration). Click here for Day 1 and Day 2.
Times are linked to a time converter site to view alternate time zones.
Papers in each session are listed below.
| Day1 | May 26, 2022 |
|---|---|
| Time (Dublin) | Session |
| 09:00-09:10am | Welcome Remarks |
| 09:10-10:30 | Findings of the IWSLT 2022 Evaluation Campaign |
| 10:30-11:00 | Coffee Break |
| 11:00-12:30 | Oral 1: Scientific Papers |
| 12:30-14:00 | Lunch Break |
| 14:00-15:00 | Keynote: Frederic Chaume |
| 15:00-15:30 | Coffee Break |
| 15:30-17:30 | Poster Session: System Papers |
| 17:30 | End of Day 1 |
| Day2 | May 27, 2022 |
|---|---|
| Time (Dublin) | Session |
| 09:00-09:10am | Opening Remarks |
| 09:10-10:30 | Oral 2: Scientific Papers |
| 10:30-11:00 | Coffee Break |
| 11:00-12:00 | Discussion 1: Human evaluations |
| 12:00-14:00 | Lunch Break |
| 14:00-15:00 | Discussion 2: Retrospective |
| 15:00-15:30 | Coffee Break |
| 15:30-16:30 | Discussion 3: Planning |
| 16:30-16:45 | Best Student Paper Award |
| 16:45-17:00 | Closing Remarks |
Proceedings
Link: Paper pdfs, abstracts, and bibtex on the ACL Anthology.
Videos were tested to play on Chrome.
Oral Session 1
| Time (Dublin) | Paper |
| 11:00-11:18am |
SubER - A Metric for Automatic Evaluation of Subtitle Quality Authors: Patrick Wilken [p], Panayota Georgakopoulou and Evgeny Matusov Video: Link |
| 11:18-11:36am |
Improving Arabic Diacritization by Learning to Diacritize and Translate Authors: Brian Thompson [p] and Ali Alshehri Video: Link |
| 11:36-11:54am |
Simultaneous Neural Machine Translation with Prefix Alignment Authors: Yasumasa Kano [r], Katsuhito Sudoh and Satoshi Nakamura Video: Link |
| 11:54-12:12pm |
Locality-Sensitive Hashing for Long Context Neural Machine Translation Authors: Frithjof Petrick [p], Jan Rosendahl, Christian Herold and Hermann Ney Video: Link |
| 12:12-12:30pm |
Who Are We Talking About? Handling Person Names in Speech Translation Authors: Marco Gaido [r], Matteo Negri and Marco Turchi Video: Link |
Oral Session 2
| Time (Dublin) | Paper |
| 09:10-09:30am |
Anticipation-Free Training for Simultaneous Machine Translation Authors: Chih-Chiang Chang [r], Shun-Po Chuang and Hung-yi Lee Video: Link |
| 09:30-09:50am |
Joint Generation of Captions and Subtitles with Dual Decoding Authors: Jitao Xu [r], François Buet [r], Josep Crego, Elise Bertin-Lemée and François Yvon Video: Link |
| 09:50-10:10am |
MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning Authors: Di Wu [r], Liang Ding, Shuo Yang, Mingyang Li Video: Link |
| 10:10-10:30am |
On the Impact of Noises in Crowd-Sourced Data for Speech Translation Authors: Siqi Ouyang [r], Rong Ye and Lei Li Video: Link |
Poster Session
The YiTrans Neural Speech Translation Systems for IWSLT 2022 Offline Shared Task.
Authors: Ziqiang Zhang and Junyi Ao [r].
Video: Link
Amazon Alexa AI’s System for IWSLT 2022 Offline Speech Translation Shared Task.
Authors: Akshaya Vishnu Kudlu Shanbhogue [r], Ran Xue, Ching-Yun Chang and Sarah Campbell
Video: Link
Efficient yet Competitive Speech Translation: FBK@IWSLT2022.
Authors: Marco Gaido [r], Sara Papi, Dennis Fucci, Giuseppe Fiameni, Matteo Negri and Marco Turchi.
Video: Link
Effective combination of pretrained models - KIT@IWSLT2022.
Authors: Ngoc-Quan Pham, Tuan Nam Nguyen, Thai-Binh Nguyen, Danni Liu, Carlos Mullov [p], Jan Niehues and Alexander Waibel
Video: Link
The USTC-NELSLIP Offline Speech Translation Systems for IWSLT 2022.
Authors: Weitai Zhang [r], Zhongyi Ye, Haitao Tang, Xiaoxi Li, Xinyuan Zhou, Jing Yang, Jianwei Cui, Dan Liu, Junhua Liu and Lirong Dai.
Video: Link
The AISP-SJTU Simultaneous Translation System for IWSLT 2022.
Authors: Qinpei Zhu [r], Renshou Wu, Guangfeng Liu, Xinyu Zhu, Xingyu Chen, Yang Zhou, Qingliang Miao, Rui Wang and Kai Yu.
Video: Link
The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022.
Authors: Bao Guo [r], Mengge Liu, Wen Zhang, Hexuan Chen, Chang Mu, Xiang Li, Jianwei Cui, Bin Wang and Yuhang Guo.
Video: Link
NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2022.
Authors: Oleksii Hrinchuk [r], Vahid Noroozi, Abhinav Khattar, Anton Peganov, Sandeep Subramanian, Somshubra Majumdar and Oleksii Kuchaiev.
Video: Link
The NiuTrans’s Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task.
Authors: Yuhao Zhang [r], Canan Huang, Chen Xu, Xiaoqian Liu, Bei Li, Anxiang Ma, Tong Xiao and Jingbo Zhu.
Video: Link
The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation.
Authors: Yinglu Li, Minghan Wang [r], Jiaxin GUO, Xiaosong Qiao, Yuxia Wang, Daimeng Wei, Chang Su, Yimeng Chen, Min Zhang, shimin tao, Hao Yang and Ying Qin
Video: Link
The HW-TSC’s Simultaneous Speech Translation System for IWSLT 2022 Evaluation.
Authors: Minghan Wang [r], Jiaxin GUO, Yinglu Li, Xiaosong Qiao, Yuxia Wang, Zongyao Li, Chang Su, Yimeng Chen, Min Zhang, shimin tao, Hao Yang and Ying Qin
Video: Link
MLLP-VRAIN UPV systems for the IWSLT 2022 Simultaneous Speech Translation and Speech-to-Speech Translation tasks.
Authors: Javier Iranzo-Sánchez [p], Javier Jorge Cano, Alejandro Pérez-González-de-Martos, Adrián Giménez Pastor, Gonçal Garcés Díaz-Munío, Pau Baquero-Arnal, Joan Albert Silvestre-Cerdà, Jorge Civera Saiz, Albert Sanchis and Alfons Juan
Video: Link
Pretrained Speech Encoders and Efficient Fine-tuning Methods for Speech Translation: UPC at IWSLT 2022.
Authors: Ioannis Tsiamas [p], Gerard I. Gállego [p], Carlos Escolano, José A. R. Fonollosa and Marta R. Costa-jussà.
Video: Link
CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022.
Authors: Peter Polák [p], Ngoc-Quan Pham, Tuan Nam Nguyen, Danni Liu, Carlos Mullov, Jan Niehues, Ondřej Bojar and Alexander Waibel.
Video: Link
NAIST Simultaneous Speech-to-Text Translation System for IWSLT 2022.
Authors: Ryo Fukuda [r], Yuka Ko, Yasumasa Kano, Kosuke Doi, Hirotaka Tokuyama, Sakriani Sakti, Katsuhito Sudoh and Satoshi Nakamura.
Video: Link
The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation.
Authors: Jiaxin GUO, Yinglu Li, Minghan Wang [r], Xiaosong Qiao, Yuxia Wang, Hengchao Shang, Chang Su, Yimeng Chen, Min Zhang, shimin tao, Hao Yang and Ying Qin
Video: Link
CMU’s IWSLT 2022 Dialect Speech Translation System.
Authors: Brian Yan [r], Patrick Fernandes, Siddharth Dalmia, Jiatong Shi, Yifan Peng, Dan Berrebbi, Xinyi Wang, Graham Neubig and Shinji Watanabe.
Video: Link
ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks.
Authors: Marcely Zanon Boito [p], John Ortega, Hugo Riguidel, Antoine LAURENT, Loïc Barrault, Fethi Bougares, Firas Chaabani, Ha Nguyen, Florentin Barbier, SOUHIR GAHBICHE and Yannick Estève.
Video: Link
JHU IWSLT 2022 Dialect Speech Translation System Description.
Authors: Jinyi Yang, Amir Hussein, Matthew Wiesner [r] and Sanjeev Khudanpur.
Video: Link
Controlling Translation Formality Using Pre-trained Multilingual Language Models.
Authors: Elijah Rippeth [p], Sweta Agrawal and Marine Carpuat
Video: Link
Controlling Formality in Low-Resource NMT with Domain Adaptation and Re-Ranking: SLT-CDT-UoS at IWSLT2022.
Authors: Sebastian Vincent [p], Loïc Barrault and Carolina Scarton.
Video: Link
Improving Machine Translation Formality Control with Weakly-Labelled Data Augmentation and Post Editing Strategies.
Authors: Daniel Zhang, Jiang Yu [r], Pragati Verma, Ashwinkumar Ganesan and Sarah Campbell
Video: Link
HW-TSC’s Participation in the IWSLT 2022 Isometric Spoken Language Translation.
Authors: Zongyao Li, JiaXin Guo, Daimeng Wei, Hengchao Shang, Minghan Wang, Ting Zhu, Zhanglin Wu, Zhengzhe Yu, Xiaoyu Chen, Lizhi Lei, Hao Yang and Ying Qin
Video:
AppTek’s Submission to the IWSLT 2022 Isometric Spoken Language Translation Task.
Authors: Patrick Wilken and Evgeny Matusov [p]
Video: Link
Hierarchical Multi-task learning framework for Isometric-Speech Language Translation.
Authors: Aakash Bhatnagar, Nidhir Bhavsar, Muskaan Singh and Petr Motlicek
Video: