Neural Response Generation with Meta-Words
This addresses the challenge of generating varied and explainable responses in chatbots, representing an incremental advance with a novel method for a known bottleneck.
The paper tackles the problem of generating diverse and controllable responses in open-domain dialogues by introducing meta-words to model one-to-many relationships, resulting in significant improvements over state-of-the-art models in metrics like relevance, diversity, and accuracy.
We present open domain response generation with meta-words. A meta-word is a structured record that describes various attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues and perform response generation in an explainable and controllable manner. To incorporate meta-words into generation, we enhance the sequence-to-sequence architecture with a goal tracking memory network that formalizes meta-word expression as a goal and manages the generation process to achieve the goal with a state memory panel and a state controller. Experimental results on two large-scale datasets indicate that our model can significantly outperform several state-of-the-art generation models in terms of response relevance, response diversity, accuracy of one-to-many modeling, accuracy of meta-word expression, and human evaluation.