Neural-based Natural Language Generation in Dialogue using RNN Encoder-Decoder with Semantic Aggregation
This work addresses NLG for spoken dialogue systems, offering incremental improvements in performance.
The paper tackles natural language generation in dialogue systems by proposing an Encoder-Aggregator-Decoder model with a Semantic Aggregator, which consistently outperforms previous methods across four domains.
Natural language generation (NLG) is an important component in spoken dialogue systems. This paper presents a model called Encoder-Aggregator-Decoder which is an extension of an Recurrent Neural Network based Encoder-Decoder architecture. The proposed Semantic Aggregator consists of two components: an Aligner and a Refiner. The Aligner is a conventional attention calculated over the encoded input information, while the Refiner is another attention or gating mechanism stacked over the attentive Aligner in order to further select and aggregate the semantic elements. The proposed model can be jointly trained both sentence planning and surface realization to produce natural language utterances. The model was extensively assessed on four different NLG domains, in which the experimental results showed that the proposed generator consistently outperforms the previous methods on all the NLG domains.