AMTA2020
Conference of the Association of Machine Translation in the Americas
The 14th biennial conference of the Association of Machine Translation in the Americas (AMTA 2020) was hosted online from 5 October to 9 October, 2020.
Proceedings
Schedule
Day 1
Monday, 5 October, 20220304
12:00 - 20:00 | Opening Reception Networking Area |
Day 2
Tuesday, 6 October, 2020
8:00 - 11:00 | Tutorial: Quick-Start Guide to Understanding and Working with Machine Translation Adam Wooten |
Tutorial: NMT Domain Adaptation Techniques Yasmin Moslem | |
08:00 - 10:10 | Workshop: Virtual Workshop on the Impact of Machine Translation (iMpacT 2020) Sharon O’Brien, Michel Simard |
10:30 - 12:30 | Workshop: Virtual Workshop on the Impact of Machine Translation (iMpacT 2020) (continued) Sharon O’Brien, Michel Simard |
12:00 - 15:00 | Tutorial: Human Parity Demystified - How Models and Data Achieve Improved Translation Quality Christian Federmann |
Workshop: 1st Workshop on Post-Editing in Modern-Day Translation (PEMDT1) John E. Ortega, Marcello Federico, Constantin Orasan, Maja Popovic |
Day 3
Wednesday, 7 October, 2020
08:00 - 08:10 | Opening |
08:10 - 08-50 | Keynote: MT Developments in the European Union Andy Way |
08:50 - 09:00 | 🕑 |
09:00 - 09:30 | Commercial User Track: Operationalizing MT quality estimation Miklos Urban, Maribel Rodríguez Molina |
Research Track: A New Approach to Parameter-Sharing in Machine Translation Benyamin Ahmadnia, Bonnie Dorr | |
09:30 - 10:00 | Commercial User Track: In search of an acceptability/unacceptability threshold in machine translation post-editing automated metrics Lucía Guerrero |
Research Track: Investigation of Transformer-based Latent Attention Models for Neural Machine Translation Parnia Bahar, Nikita Makarov, Hermann Ney | |
10:00 - 10:30 | Commercial User Track: A Survey of Qualitative Error Analysis for Neural Machine Translation Systems Denise Díaz, James Cross, Vishrav Chaudhary, Ahmed Kishky, Philipp Koehn |
Research Track: Machine Translation with Unsupervised Length-Constraints Jan Niehues | |
10:30 - 11:00 | Commercial User Track: COMET - Deploying a New State-of-the-art MT Evaluation Metric in Production Craig Stewart, Ricardo Rei, Catarina Farinha, Alon Lavie |
Research Track: Constraining the Transformer NMT Model with Heuristic Grid Beam Search Guodong Xie, Andy Way | |
11:00 - 11:30 | Demo 1 - Intento |
11:30 - 12:00 | Demo 2 - Systran |
12:00 - 12:50 | Keynote: Faithful NLG in an era of Ethical Awareness: Opportunities for MT Mona Diab |
12:50 - 13:00 | 🕑 |
13:00 - 13:30 | Commercial User Track: Scaling up automatic translation for software: reduction of post-editing volume with well-defined customer impact Dag Schmidtke |
Research Track: Machine Translation System Selection from Bandit Feedback Jason Naradowsky, Xuan Zhang, Kevin Duh | |
13:30 - 14:00 | Commercial User Track: Auto MT Quality Prediction Solution and Best Practice Martin Lei Xiao, York Jin |
Research Track: Generative latent neural models for automatic word alignment Anh Khoa Ngo Ho, Franc ̧ois Yvon | |
14:00 - 14:30 | Commercial User Track: A language comparison of human evaluation & quality estimation Silvio Picinini, Adam Bittlingmayer |
Research Track: The Impact of Indirect Machine Translation on Sentiment Classification Alberto Poncelas, Pintu Lohar, James Hadley, Andy Way | |
14:30 - 15:00 | Commercial User Track: Machine translation quality across demographic dialectal variation in Social Media Adithya Renduchintala, Dmitriy Genzel |
Research Track: Towards Handling Compositionality in Low-Resource Bilingual Word Induction Viktor Hangya, Alexander Fraser | |
15:00 - 15:10 | 🕑 |
15:10 - 16:15 | Student Mentoring Session |
Day 4
Thursday, 8 October, 2020
08:00 - 08:10 | Opening |
08:10 - 08-50 | Keynote: Factor 1000: Better MT, more content, and what we can do with it Chris Wendt |
08:50 - 09:00 | 🕑 |
09:00 - 09:30 | Commercial User Track: Making the business case for adopting MT Rodrigo Cristina |
Research Track: The OpenNMT Neural Machine Translation Toolkit: 2020 Edition Guillaume Klein, François Hernandez, Vincent Nguyen, Jean Senellart | |
09:30 - 10:00 | Commercial User Track: Flexible Customization of a Single Neural Machine Translation System with Multi-dimensional Metadata Inputs Evgeny Matusov, Patrick Wilken, Christian Herold |
Research Track: The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020 Tobias Domhan, Michael Denkowski, David Vilar, Xing Niu, Felix Hieber, Kenneth Heafield | |
10:00 - 10:30 | Commercial User Track: **Enhance CX with Neural Machine Translation Technology Rubén Martínez-Domínguez, Matíss Rikters, Artūrs Vasiļevskis, Mārcis Pinnis, Paula Reichenberg |
Research Track: THUMT: An Open-Source Toolkit for Neural Machine Translation Zhixing Tan, Jiacheng Zhang, Xuancheng Huang, Gang Chen, Shuo Wang, Maosong Sun, Huanbo Luan, Yang Liu | |
10:30 - 11:00 | Commercial User Track: Machine Translation Hype, Crash-Tested by Translation Students Jon Ritzdorf |
Research Track: Panel on Open Source NMT Toolkit Development Moderator: Matt Post | |
11:00 - 11:30 | Demo 3 - Amazon |
11:30 - 12:00 | Demo 4 - XTM |
12:00 - 12:50 | Keynote: Navigating Change: Keys to implementing language technology in government Danielle Silverman |
12:50 - 13:00 | 🕑 |
13:00 - 13:30 | Commercial User Track: Use MT to Simplify and Speed Up Your Alignment for TM Creation Judith Klein |
Research Track: Successful Tech Transfer of MT Research in Government Kathy Baker | |
13:30 - 14:00 | Commercial User Track: Selection of MT System in Translation Workflows Aleš Tamchyna |
Research Track: Plugging into Trados: Augmenting Translation in the Enclave Corey Miller, Chiara Higgins, Paige Havens, Steven Van Guilder, Rodney Morris, Danielle Silverman | |
Commercial User Track: Beyond MT: Opening Doors for an NLP Pipeline Alex Yanishevsky | |
Research Track: PEMT for the Public Sector: Discovery, Scoping, and Delivery Konstantine Boukhvalov, Eileen Block | |
Commercial User Track: Building Multi-Purpose MT Portfolio Konstantin Savenkov | |
15:00 - 15:10 | 🕑 |
15:10 - 16:30 | AMTA Business Meeting |
Day 5
Friday, 9 October, 2020
07:50 - 08:00 | Opening |
08:00 - 08:50 | Keynote: *Using language technology to enable two-way communication in humanitarian assistance Eric Paquin |
08:50 - 09:00 | 🕑 |
09:00 - 09:30 | Government Track: A Tale of Eight Countries or the EU Council Presidency Translator in Retrospect (slides) Mārcis Pinnis, Toms Bergmanis, Kristīne Metuzāle, Valters Šics, Artūrs Vasiļevskis, Andrejs Vasiļjevs |
09:30 - 10:00 | Government Track: American Sign Language (ASL) to English Machine Translation Patricia O’Neill-Brown |
09:00 - 10:00 | Student Mentoring Session |
10:00 - 10:30 | Government Track: Why is it so Hard to Develop Comparable Translation Evaluations and How Can Standards Help? Jennifer DeCamp |
Commercial User Track: Simultaneous Speech Translation in Google Translate Jeff Pitman | |
10:30 - 11:00 | Government Track: Using Contemporary US Government Data to Train Custom MT for COVID-19 Achim Ruopp |
Commercial User Track: Understanding Challenges to Enterprise Machine Translation Adoption Bart Mączyński | |
11:00 - 11:30 | Demo 5 - Facebook |
11:30 - 12:00 | Demo 5 - CustomMT |
12:00 - 12:50 | Keynote: Research stories from Google Translate’s Transcribe Mode Colin Cherry |
12:50 - 13:00 | 🕑 |
Commercial User Track: Lexically Constrained Decoding for Sequence Generation Tony O’Dowd | |
Research Track: Dynamic Masking for Improved Stability in Online Spoken Language Translation Yuekun Yao, Barry Haddow | |
Commercial User Track: Building Salesforce Neural Machine Translation System Kazuma Hashimoto, Raffaella Buschiazzo, Caiming Xiong, Teresa Marxhall | |
Research Track: On Target Segmentation for Direct Speech Translation Mattia A. Di Gangi, Marco Gaido, Matteo Negri, Marco Turchi | |
Commercial User Track: **Interactive Adaptation of Neural MT on Commercial Datasets Patrick Simianer, Joern Wuebker, John DeNero | |
Research Track: Domain Robustness in Neural Machine Translation Mathias Müller, Annette Rios, Rico Sennrich | |
Commercial User Track: **Enabling New MT Post-Editing Scenarios with Continuous Localization Igor Afanasyev | |
Research Track: Low-Resource NMT: an Empirical Study on the Effect of Rich Morphological Word Segmentation on Inuktitut Tan Ngoc, Fatiha Sadat |