Neural Response Generation with Meta-Words

06/14/2019
by   Can Xu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/30/2017

Neural Response Generation with Dynamic Vocabularies

We study response generation for open domain conversation in chatbots. E...
research
05/31/2019

Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation

Various encoder-decoder models have been applied to response generation ...
research
09/26/2019

Low-Resource Response Generation with Template Prior

We study open domain response generation with limited message-response p...
research
04/04/2020

Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks

We study multi-turn response generation for open-domain dialogues. The e...
research
03/10/2023

Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?

During the patient's hospitalization, the physician must record daily ob...
research
08/28/2018

Why Do Neural Response Generation Models Prefer Universal Replies?

Recent advances in sequence-to-sequence learning reveal a purely data-dr...
research
11/02/2018

Meta-path Augmented Response Generation

We propose a chatbot, namely Mocha to make good use of relevant entities...

Please sign up or login with your details

Forgot password? Click here to reset