Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders
arXiv:1805.04843
Abstract
Asking good questions in large-scale, open-domain conversational systems is quite significant yet rather untouched. This task, substantially different from traditional question generation, requires to question not only with various patterns but also on diverse and relevant topics. We observe that a good question is a natural composition of {\it interrogatives}, {\it topic words}, and {\it ordinary words}. Interrogatives lexicalize the pattern of questioning, topic words address the key information for topic transition in dialogue, and ordinary words play syntactical and grammatical roles in making a natural sentence. We devise two typed decoders (\textit{soft typed decoder} and \textit{hard typed decoder}) in which a type distribution over the three types is estimated and used to modulate the final generation distribution. Extensive experiments show that the typed decoders outperform state-of-the-art baselines and can generate more meaningful questions.
arXiv commentACL2018
References in corpus (12)
- Sequence to Sequence Learning with Neural Networks
- Categorical Reparameterization with Gumbel-Softmax
- Topic Aware Neural Response Generation
- A Diversity-Promoting Objective Function for Neural Conversation Models
- Question Answering and Question Generation as Dual Tasks
- Learning to Ask: Neural Question Generation for Reading Comprehension
- A Joint Model for Question Answering and Question Generation
- Learning through Dialogue Interactions by Asking Questions
- A Unified Query-based Generative Model for Question Generation and Question Answering
- Neural Models for Key Phrase Detection and Question Generation
- Neural Question Generation from Text: A Preliminary Study
- Affect-LM: A Neural Language Model for Customizable Affective Text Generation