Neural Responding Machine for Short-Text Conversation
This addresses the challenge of automated conversation generation for applications like chatbots, though it is incremental as it builds on existing encoder-decoder methods.
The paper tackled the problem of generating responses for short-text conversations by proposing the Neural Responding Machine (NRM), a neural network-based model using an encoder-decoder framework with RNNs, which achieved over 75% grammatically correct and appropriate responses, outperforming state-of-the-art retrieval-based and SMT-based models.
We propose Neural Responding Machine (NRM), a neural network-based response generator for Short-Text Conversation. NRM takes the general encoder-decoder framework: it formalizes the generation of response as a decoding process based on the latent representation of the input text, while both encoding and decoding are realized with recurrent neural networks (RNN). The NRM is trained with a large amount of one-round conversation data collected from a microblogging service. Empirical study shows that NRM can generate grammatically correct and content-wise appropriate responses to over 75% of the input text, outperforming state-of-the-arts in the same setting, including retrieval-based and SMT-based models.