Recent advances in neural machine translation - Marcin Chochowski
834 views · Published 13 November 2017 · 27:08 · Indexed 22 September 2026
Channel: PyData · 2017 · Science & Technology
Description In last few years the quality of machine translation has significantly increased. The first step that pushed that technology forward was the introduction of recurrent neural networks, the second - making them deeper. The presentation will go through the the recent advances in neural machine translation as well as the challenges that are still unsolved. Abstract In the last two years there has been a lot of hype around the Neural Machine Translation. Is it really that good, and how actually does it work? In this short presentation I will shed some light on what Neural Machine Translation is and how it works. I will go through some popular approaches and describe the recently obtained results. Finally, there will be some hints on what it has to do with Python. www.pydata.org PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome! 00:10 Help us add time stamps or captions to this video! See the description for details. Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps
More from this channel
-
41:50
Shawn Scully: Creating an intelligent world at Dato
-
24:46
Dino Viehland & Raymond Laghaeian: Jupyter Notebooks and ML Model Operationalization
-
34:32
Scott Sanderson: Developing an Expression Language for Quantitative Financial Modeling
-
44:04
Cornelia Levy-Bencheton (Keynote): The Pain of Discipline and the Power of Not Yet
-
39:28
Sergii Khomenko - From Data Science to Production - deploy, scale, enjoy!
-
38:29
Simon Byrne - Julia for data analysis
-
49:10
Rui Miguel Forte - The CV: A Data Scientist's View
-
28:01
Ruby Childs & Nick Sorros - Making Recommendations without Data