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

TL;DR

This paper introduces a novel approach for open-domain response generation using content word sequences as intermediate representations, improving content relevance and grammatical correctness in generated responses.

Contribution

It proposes a content word-based decoding method and a new evaluation metric focusing on content relevance, addressing limitations of traditional models.

Findings

Enhanced content relevance in generated responses

Better grammatical correctness for content words

Content-based evaluation correlates with response quality

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.