2019/08/27 by Heriberto Cuayáhuitl, Cuayáhuitl, Heriberto, Donghyeon Lee +11 · 2 citations
Computer Science · #AI in Service Interactions #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Speech and dialogue systems #Topic Modeling #cs.AI #cs.CL #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.1908.10331
In International Joint Conference of Neural Networks (IJCNN), 2019
openalex created_date 2019/06/27 · arxiv created 2019/08/27 · openalex publication_date 2019/08/27 · arxiv updated 2019/08/28 · openalex updated_date 2026/07/28
Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead of infinite actions, and a simple but promising reward function based on human-likeness scores derived from human-human dialogue data. We train Deep Reinforcement Learning (DRL) agents using chitchat data in raw text---without any manual annotations. Experimental results using different splits of training data report the following. First, that our agents learn reasonable policies in the environments they get familiarised with, but their performance drops substantially when they are exposed to a test set of unseen dialogues. Second, that the choice of sentence embedding size between 100 and 300 dimensions is not significantly different on test data. Third, that our proposed human-likeness rewards are reasonable for training chatbots as long as they use lengthy dialogue histories of >=10 sentences.