Pith. sign in

REVIEW 2 cited by

A Deep Reinforcement Learning Chatbot (Short Version)

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1801.06700 v1 pith:EZXYI3JW submitted 2018-01-20 cs.CL cs.AIcs.LGcs.NEstat.ML

classification cs.CLcs.AIcs.LGcs.NEstat.ML
keywords learningreinforcementdeepensemblemodelsreal-worldsystembeen
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including neural network and template-based models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than other systems. The results highlight the potential of coupling ensemble systems with deep reinforcement learning as a fruitful path for developing real-world, open-domain conversational agents.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Ensemble-Based Deep Reinforcement Learning for Chatbots

    cs.AI 2019-08 conditional novelty 6.0 of 10

    A response-selection chatbot trained as an ensemble of 100 deep reinforcement learning agents, each on a cluster of dialogues, outperforms a single DRL agent and a Seq2Seq baseline on Persona-Chat.

  2. Deep Reinforcement Learning for Chatbots Using Clustered Actions and Human-Likeness Rewards

    cs.AI 2019-08 conditional novelty 6.0 of 10

    A DQN chatbot that selects among 100 clustered reply types and is rewarded for picking true human responses learns on training dialogues but generalizes poorly to unseen dialogues.

Pith tools