Natural Language Generation by Hierarchical Decoding with Linguistic Patterns
This work addresses a specific bottleneck in NLG for dialogue systems, offering an incremental improvement in efficiency and performance.
The paper tackles the problem of generating complex and long sentences in natural language generation (NLG) for spoken dialogue systems by introducing a hierarchical decoding model based on linguistic patterns, which outperforms traditional encoder-decoder models with a smaller model size.
Natural language generation (NLG) is a critical component in spoken dialogue systems. Classic NLG can be divided into two phases: (1) sentence planning: deciding on the overall sentence structure, (2) surface realization: determining specific word forms and flattening the sentence structure into a string. Many simple NLG models are based on recurrent neural networks (RNN) and sequence-to-sequence (seq2seq) model, which basically contains an encoder-decoder structure; these NLG models generate sentences from scratch by jointly optimizing sentence planning and surface realization using a simple cross entropy loss training criterion. However, the simple encoder-decoder architecture usually suffers from generating complex and long sentences, because the decoder has to learn all grammar and diction knowledge. This paper introduces a hierarchical decoding NLG model based on linguistic patterns in different levels, and shows that the proposed method outperforms the traditional one with a smaller model size. Furthermore, the design of the hierarchical decoding is flexible and easily-extensible in various NLG systems.