For example, users have determined the departure, the destination, and the travel time for booking a flight.
Learning discrete dialog structure graph from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation.
Learning interpretable dialog structure from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation.
With the transformation of education from the traditional classroom environment to online education and assessment, it is more and more important to accurately assess the difficulty of questions than ever.
Furthermore, to facilitate the convergence of Gaussian mixture prior and posterior distributions, we devise a curriculum optimization strategy to progressively train the model under multiple training criteria from easy to hard.
The sequence-to-sequence (Seq2Seq) model generates target words iteratively given the previously observed words during decoding process, which results in the loss of the holistic semantics in the target response and the complete semantic relationship between responses and dialogue histories.
Deep learning approaches for sentiment classification do not fully exploit sentiment linguistic knowledge.
Ranked #4 on Sentiment Analysis on MR
In this study, we explore capsule networks with dynamic routing for text classification.
Ranked #6 on Sentiment Analysis on MR