Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems

TL;DR

This paper introduces a semantically conditioned LSTM-based natural language generator for spoken dialogue systems that improves naturalness and informativeness over traditional rule-based methods, with better scalability and language variation.

Contribution

It presents a novel LSTM-based generator that learns from unaligned data, jointly optimizes sentence planning and realization, and enhances language variation and naturalness.

Findings

Outperforms previous methods in objective evaluations.

Human judges rated it higher for naturalness and informativeness.

Demonstrates effectiveness across multiple domains.

Abstract

Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and stylised responses without the natural variation of human language. They are also not easily scaled to systems covering multiple domains and languages. This paper presents a statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure. The LSTM generator can learn from unaligned data by jointly optimising sentence planning and surface realisation using a simple cross entropy training criterion, and language variation can be easily achieved by sampling from output candidates. With fewer heuristics, an objective evaluation in two differing test domains showed the proposed method improved performance compared to previous methods. Human judges scored the LSTM system higher on informativeness and naturalness and overall preferred it to the other systems.