28 citations
- Georgia Institute of TechnologyUS2 papers
- Meta (Israel)IL2 papers
- RWTH Aachen UniversityDE2 papers
- Aalto UniversityFI1 paper
- Academy of Performing Arts in PragueCZ1 paper
- Agence Parisienne du ClimatFR1 paper
- Amazon (Germany)DE1 paper
- Amirkabir University of TechnologyIR1 paper
- Amsterdam University CollegeNL1 paper
- Amsterdam University of Applied SciencesNL1 paper
- Association for Computing MachineryUS1 paper
- Astrophysique, Instrumentation et ModélisationFR1 paper
4 papers · 1 filter
Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang +4
Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models. However, cascaded models are known to be prone to error…
Back-translation for Large-Scale Multilingual Machine Translation
Baohao Liao, Shahram Khadivi, Sanjika Hewavitharana
This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). This work aims to bu…
Conditional Sequential Slate Optimization
Yipeng Zhang, Mingjian Lu, Saratchandra Indrakanti +2
The top search results matching a user query that are displayed on the first page are critical to the effectiveness and perception of a search system. A search ranking system typic…
eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition Challenges
Jiangbo Yuan, An-Ti Chiang, Wen Tang +1
Large-scale product recognition is one of the major applications of computer vision and machine learning in the e-commerce domain. Since the number of products is typically much la…