SerbanI.V. x 6

bookRéférences 6

The first conversational intelligence challenge

The first Conversational Intelligence Challenge was conducted over 2017 with finals at NIPS conferen...

2025-09-13 20:18:00

SerbanI.V.BurtsevM.LogachevaV.MalykhV.

A deep reinforcement learning chatbot (short version)

… negative sentiment, where Qlearning AMT consistently obtained the lowest percentage of ...

2018-01-22 20:05:07

SerbanI.V.SankarC.ZhangS.GermainM.

Towards an automatic turing test: Learning to evaluate dialogue responses

Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging...

2018-01-17 20:02:38

LoweR.SerbanI.V.NoseworthyM.

The octopus approach to the Alexa competition: A deep ensemble-based socialbot

… This is supported by the percentage of user utterances with positive and negative senti...

2017-12-07 18:40:23

LinZ.SerbanI.V.SankarC.ZhangS.

A deep reinforcement learning chatbot

… For our purpose, we propose a simple variant of reward shaping which takes into account...

2017-11-06 20:11:22

SerbanI.V.SankarC.ZhangS.GermainM.

The bottleneck simulator: A model-based deep reinforcement learning approach

… sentiment and ZGeneric user utterance. Although we only consider dialogue acts, sentime...

SerbanI.V.SankarC.PieperM.PineauJ.

Mots-clés associés