|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
However, previous work in dialogue response generation has shown that these metrics do not correlate strongly with human judgment in the non task-oriented dialogue setting.
This paper presents a new adversarial learning method for generative conversational agents (GCA) besides a new model of GCA.
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens.
Human generates responses relying on semantic and functional dependencies, including coreference relation, among dialogue elements and their context.
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses.
In this paper, drawing intuition from the Turing test, we propose using adversarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishable from human-generated dialogue utterances.
SOTA for Dialogue Generation on Amazon-5
The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains.
We propose several strong multimodal baselines and show the importance of contextual and multimodal information for emotion recognition in conversations.
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.
Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge.