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

TLDR

Natural language generation is essential for spoken dialogue, yet existing rule‑based systems produce rigid, stylised responses and struggle to scale across domains and languages. The study introduces a semantically conditioned LSTM‑based statistical language generator. The LSTM learns from unaligned data by jointly optimizing sentence planning and surface realisation with cross‑entropy training, enabling easy language variation through sampling from output candidates. Objective evaluation in two domains showed improved performance over prior methods, and human judges rated the LSTM system higher on informativeness, naturalness, and overall preference.

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.