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

Abstract

Various encoder-decoder models have been applied to response generation in open-domain dialogs, but a majority of conventional models directly learn a mapping from lexical input to lexical output without explicitly modeling intermediate representations. Utilizing language hierarchy and modeling intermediate information have been shown to benefit many language understanding and generation tasks. Motivated by Broca's aphasia, we propose to use a content word sequence as an intermediate representation for open-domain response generation. Experimental results show that the proposed method improves content relatedness of produced responses, and our models can often choose correct grammar for generated content words. Meanwhile, instead of evaluating complete sentences, we propose to compute conventional metrics on content word sequences, which is a better indicator of content relevance.

13 pages, 2 figures, 8 tables (rejected by ACL 2019)

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• A Neural Conversational Model
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• A Latent Variable Recurrent Neural Network for Discourse Relation Language Models
• Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
• Neural Response Generation with Dynamic Vocabularies
• Latent Intention Dialogue Models