Natural Language Generation for Spoken Dialogue System using RNN Encoder-Decoder Networks
This work addresses NLG for spoken dialogue systems, showing incremental improvements in performance and generalization.
The paper tackled natural language generation for spoken dialogue systems by proposing an RNN encoder-decoder with an LSTM-based decoder and attention mechanism, achieving consistent outperformance over previous methods across four NLG datasets and demonstrating generalization to unseen domains.
Natural language generation (NLG) is a critical component in a spoken dialogue system. This paper presents a Recurrent Neural Network based Encoder-Decoder architecture, in which an LSTM-based decoder is introduced to select, aggregate semantic elements produced by an attention mechanism over the input elements, and to produce the required utterances. The proposed generator can be jointly trained both sentence planning and surface realization to produce natural language sentences. The proposed model was extensively evaluated on four different NLG datasets. The experimental results showed that the proposed generators not only consistently outperform the previous methods across all the NLG domains but also show an ability to generalize from a new, unseen domain and learn from multi-domain datasets.