Wizard of Wikipedia: Knowledge-Powered Conversational agents · HackerPapers discussions

Wizard of Wikipedia: Knowledge-Powered Conversational agents — mentioned by ekdinan

Wed, 06 May 2020 19:52:28 GMT

One of the tasks that we fine-tuned the model on is ConvAI2 (or "Persona-chat") which specifically aims to improve the model's consistency by conditioning its responses on a given persona. See here: https://arxiv.org/abs/1801.07243. In this research we found that conditioning on a persona improves consistency, but that the models still aren't always perfectly consistent. In particular, the model can only see a few turns back in the dialogue history, and may contradict itself if the conversation is long enough that the model simply does not see the full conversation. As far as facts go, we…

Paper and discussion history. A mention is not an endorsement.

Wizard of Wikipedia: Knowledge-Powered Conversational agents — mentioned by slashcom

Fri, 02 Aug 2019 17:51:17 GMT

Links to papers: https://arxiv.org/abs/1811.00207 - Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset https://arxiv.org/abs/1811.01241 - Wizard of Wikipedia: Knowledge-Powered Conversational agents https://arxiv.org/abs/1810.10665 - Engaging Image Captioning Via Personality https://arxiv.org/abs/1902.08654 - What makes a good conversation? How controllable attributes affect human judgments And a demo of a bot that they've produced: https://www.facebook.com/Beat-The-Bot-212188996195556/

Paper and discussion history. A mention is not an endorsement.