December 12, 2019
We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots. Some key takeaways from the competition are: (i) pretrained Transformer variants are currently the best performing models on this task, (ii) but to improve performance on multi-turn conversations with humans, future systems must go beyond single word metrics like perplexity to measure the performance across sequences of utterances (conversations) – in terms of repetition, consistency and balance of dialogue acts (e.g. how many questions asked vs. answered).
Written by
Arthur Szlam
Jack Urbanek
Kurt Shuster
Ryan Lowe
Alan W Black
Alexander Rudnicky
Iulian Servan
Jason Williams
Mikhail Burtsev
Shrimai Prabhumoye
Valentin Malykh
Varvara Logacheva
Yoshua Bengio
Publisher
The Springer Series on Challenges in Machine Learning
April 23, 2024
Sachit Menon, Ishan Misra, Rohit Girdhar
April 23, 2024
February 13, 2024
Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht, Natalia Neverova, Andrea Vedaldi, Oran Gafni, Filippos Kokkinos
February 13, 2024
December 26, 2023
Lior Yariv, Omri Puny, Natalia Neverova, Oran Gafni, Yaron Lipman
December 26, 2023
August 10, 2023
Samaneh Azadi, Akbar Shah, Devi Parikh, Sonal Gupta, Thomas Hayes
August 10, 2023
Product experiences
Foundational models
Product experiences
Latest news
Foundational models