MT Summit 2019
Machine Translation Summit
MT Summit 2019 was organised by EAMT.
Location
- Dublin, Ireland
Schedule
Day 1
| 9:00 | Opening ceremony |
| 570.0 | Invited talk Crowdsourcing and Related Tools for Quality Monitoring in PEMT Helena Moniz |
| 10:30 | ☕️ |
| 11:00 | Research 1 (Speech and translation) |
| Online Sentence Segmentation for Simultaneous Interpretation using Multi-Shifted RNN Xiaolin Wang, Masao Utiyama, Eiichiro Sumita | |
| Robust Document Representations for CLIR in Low-Resource Settings Mahsa Yarmohammadi, Xutai Ma, Sorami Hisamoto, Muhammad Rahman, Yiming Wang, Hainan Xu, Daniel Povey, Philipp Koehn and Kevin Duh | |
| Enhancing Transformer for End-to-end Speech-to-Text Translation Mattia A. Di Gangi, Matteo Negri, Roldano Cattoni, Roberto Dessi and Marco Turchi | |
| Translators 1 (The market, the translator, the institutions) | |
| Competitiveness Analysis of the European Machine Translation Market Andrejs Vasiļjevs, Inguna Skadiņa, Indra Sāmīte, Kaspars Kauliņš, Ēriks Ajausks, Jūlija Meļņika and Aivars Bērziņš | |
| Improving CAT Tools in the Translation Workflow: New Approaches and Evaluations Mihaela Vela, Santanu Pal, Marcos Zampieri, Sudip Naskar and Josef van Genabith | |
| Hungarian translators’ perceptions of Neural Machine Translation in the European Commission Ágnes Lesznyák | |
| 12:30 | 🍴 |
| 14:00 | Poster Boaster: Users, Projects and Research |
| 15:30 | ☕️ |
| 16:00 | Poster Session |
| Research | |
| Debiasing Word Embeddings Improves Multimodal Machine Translation Tosho Hirasawa and Mamoru Komachi | |
| Translator2Vec: Understanding and Representing Human Post-Editors António Góis and André F. T. Martins | |
| Domain Adaptation for MT: A Study with Unknown and Out-of-Domain Tasks Hoang Cuong | |
| What is the impact of raw MT on Japanese users of Word: preliminary results of a usability study using eye-tracking Ana Guerberof Arenas, Joss Moorkens, Sharon O’Brien | |
| MAGMATic: A Multi-domain Academic Gold Standard with Manual Annotation of Terminology for Machine Translation Evaluation Randy Scansani, Luisa Bentivogli, Silvia Bernardini, Adriano Ferraresi | |
| Automatic error classification with multiple error labels Maja Popovic and David Vilar | |
| Users | |
| Leveraging Rule-Based Machine Translation Knowledge for Under-Resourced Neural Machine Translation Models Daniel Torregrosa, Nivranshu Pasricha, Maraim Masoud, Bharathi Raja Chakravarthi, Juan Alonso, Noe Casas, Mihael Arcan | |
| Bootstrapping a Natural Language Interface to a Cyber Security Event Collection System using a Hybrid Translation Approach Johann Roturier, Brian Schlatter, David Silva Schlatter | |
| Improving Robustness in Real-World Neural Machine Translation Engines Rohit Gupta, Patrik Lambert, Raj Patel and John Tinsley | |
| Surveying the potential of using speech technologies for post-editing purposes in the context of international organizations: What do professional translators think? Jeevanthi Liyanapathirana, Pierrette Bouillon, Bartolomé Mesa-Lao | |
| Automatic Translation for Software with Safe Velocity Dag Schmidtke and Declan Groves | |
| Application of Post-Edited Machine Translation in Fashion eCommerce Kasia Kosmaczewska and Matt Train | |
| Morphological Neural Pre- and Post-Processing for Slavic Languages Giorgio Bernardinello | |
| Large-scale Machine Translation Evaluation of the iADAATPA Project Sheila Castilho, Natália Resende, Federico Gaspari, Andy Way, Tony O’Dowd, Marek Mazur, Manuel Herranz, Alex Helle, Gema Ramírez-Sánchez, Víctor Sánchez-Cartagena, Mārcis Pinnis, Valters Šics | |
| Projects | |
| NEC TM Data Project Alexandre Helle and Manuel Herranz | |
| APE-QUEST Joachim Van den Bogaert, Heidi Depraetere, Sara Szoc, Tom Vanallemeersch, Koen Van Winckel, Frederic Everaert, Lucia Specia, Julia Ive, Maxim Khalilov, Christine Maroti, Eduardo Farah and Artur Ventura | |
| PRINCIPLE: Providing Resources in Irish, Norwegian, Croatian and Icelandic for the Purposes of Language Engineering Andy Way and Federico Gaspari | |
| iADAATPA Project: Pangeanic use cases Mercedes García-Martínez, Amando Estela, Laurent Bié, Alexandre Helle and Manuel Herranz | |
| MICE Joachim Van den Bogaert, Heidi Depraetere, Tom Vanallemeersch, Frederic Everaert, Koen Van Winckel, Katri Tammsaar, Ingmar Vali, Tambet Artma, Piret Saartee, Laura Katariina Teder, Artūrs Vasiļevskis, Valters Sics, Johan Haelterman and David Bienfait | |
| ParaCrawl: Web-scale parallel corpora for the languages of the EU Miquel Esplà, Mikel Forcada, Gema Ramírez-Sánchez, Hieu Hoang | |
| Pivot Machine Translation in INTERACT Project Chao-Hong Liu, Andy Way, Catarina Silva, André Martins | |
| Global Under-Resourced Media Translation (GoURMET) Alexandra Birch, Barry Haddow, Ivan Tito, Antonio Valerio Miceli Barone, Rachel Bawden, Felipe Sánchez-Martínez, Mikel L. Forcada, Miquel Esplà-Gomis, Víctor Sánchez-Cartagena, Juan Antonio Pérez-Ortiz, Wilker Aziz, Andrew Secker, Peggy van der Kreeft | |
| Neural machine translation system for the Kazakh language Ualsher Tukeyev, Zhandos Zhumanov |
Day 2
Day 3
| 9:00 | Research 4 (Linguistic analysis and morphology) |
| Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation Eva Vanmassenhove, Dimitar Shterionov, Andy Way | |
| Identifying Fluently Inadequate Output in Neural and Statistical Machine Translation Marianna Martindale, Marine Carpuat, Kevin Duh, Paul McNamee | |
| Character-Aware Decoder for Translation into Morphologically Rich Languages Adithya Renduchintala, Pamela Shapiro, Kevin Duh, Philipp Koehn | |
| User 2: Neural post-editing and quality estimation | |
| Raising the TM Threshold in Neural MT Post-Editing: a Case Study on Two Datasets Anna Zaretskaya | |
| Incremental Adaptation of NMT for Professional Post-editors: A User Study Miguel Domingo, Mercedes García-Martínez, Álvaro Peris, Alexandre Helle, Amando Estela, Laurent Bié, Francisco Casacuberta, Manuel Herranz | |
| When less is more in Neural Quality Estimation of Machine Translation. An industry case study Dimitar Shterionov, Félix Do Carmo, Joss Moorkens, Eric Paquin, Dag Schmidtke, Declan Groves, Andy Way | |
| 10:30 | ☕️ |
| 11:00 | Research 5 (Post-editing) |
| Improving Translations by Combining Fuzzy-Match Repair with Automatic Post-Editing John Ortega, Felipe Sánchez-Martínez, Marco Turchi, Matteo Negri | |
| Post-editing Productivity with Neural Machine Translation: An Empirical Assessment of Speed and Quality in the Banking and Finance Domain Samuel Läubli, Chantal Amrhein, Patrick Düggelin, Beatriz Gonzalez, Alena Zwahlen, Martin Volk | |
| Post-editese: an Exacerbated Translationese Antonio Toral | |
| 12:30 | 🍴 |
| 13:30 | EAMT General Assembly |
| 14:30 | IAMT General Assembly |
| 15:00 | ☕️ |
| 15:30 | Invited talk Understanding syntactic and semantic transfer in multilingual neural network models Arianna Bisazza |
| 16:30 | Closing ceremony, including IAMT Award of Honour, Best Paper Award. Announcement: EAMT 2020, MT Summit 2021 |
| 17:30 | Close |
Research track
- Advances in various MT paradigms: data-driven, rule-based, and hybrid MT
- Incorporating external knowledge (e.g. document, image, metadata etc) into MT models
- MT applications and embedding: translation/localization aids, speech-to-speech, speech-to-text, OCR
- MT for communication (chats, blogs, social networks), multilingual applications, etc
- Technologies for MT deployment: quality estimation and domain adaptation
- MT in special settings: low resources, massive resources, high volume, low computing resources, crisis scenarios, etc.
- Human factors in MT and user interfaces for MT
- Ethical issues in translation
- Linguistic resources for MT: dictionaries, terminology banks, corpora
- MT evaluation techniques and evaluation results
- Empirical studies on translation data
User track
- Analyses of the effects of applying research technology to practical application scenarios
- Descriptions of demonstrations appearing at the technology showcase
Translator track
- Productivity measurements and their impact on MT adoption
- Impact of MT on translators’ work (pricing issues, post-editing tasks assignment and their acceptance among translators)
- Ethical and confidentiality issues when using MT
- Psycho-social aspects of MT adoption (translator attitudes and [pre-]conceptions)
- Types of MT errors which influence quality acceptance/rejection
- Discussions on the role of professional translators in MT development
- The business side of MT
- Integration of MT in large-scale production processes
- The importance of translator feedback in MT
- The role of the freelance translator in MT
- The eruption of neural MT and its effect on the translation profession
Projects track
- Reports from publicly-funded research projects related to machine translation
Schedule
Tutorials
Day 1
19 August, 2019
| The unreasonable effectiveness of Neural Models in Language Decoding | Tony O’Dowd KantanMT |
| Challenge Test Sets for MT Evaluation sites.google.com/view/challenge-test-sets-tutorial/home | Maja Popovic & Sheila Castilho ADAPT Centre, DCU |
Day 2
20 August, 2019
| A Deep Learning Curve for Post-Editing 2 | Lena Marg, Tanja Langguth & Elaine O’Curran Welocalize |
| Practical Statistics for Research in Machine Translation and Translation Studies | Antonio Toral U. Groningen |