50 papers with code • 1 benchmarks • 6 datasets
To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning.
Ranked #1 on Chatbot on 10 Monkey Species (using extra training data)
One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges.
Human generates responses relying on semantic and functional dependencies, including coreference relation, among dialogue elements and their context.
In this work, we explore the application of PLATO-2 on various dialogue systems, including open-domain conversation, knowledge grounded dialogue, and task-oriented conversation.
Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes.
In this paper, we introduce the use of Semantic Hashing as embedding for the task of Intent Classification and achieve state-of-the-art performance on three frequently used benchmarks.