Post date: Nov 2, 2017 4:27:31 PM
We are happy to announce that the interest in the E2E NLG shared task has by far outperformed our expectations.
Heriot-Watt University has set out this challenge for the first time this year, and we received a total of 60 submissions by 16 institutions with about 1/3 of these submissions coming from industry.
In comparison, the well established Conference in Machine Translation WMT’17 (running since 2006) got 31 institutions submitting to a total of 8 tasks.
Institutions submitting to this challenge include top international universities, such as Harvard, University of California Santa Cruz, National Taiwan University, etc., as well as industry-based research groups, such as Google Research, Samsung, Thomson Reuters, Xerox Research etc.
The purpose of this challenge is to push frontiers in data-driven machine learning methods for generating natural system utterances in task-based conversational agents. For more information, see: