Natural language generation by hierarchical decoding with linguistic patterns
Journal
NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
Journal Volume
2
Pages
61-66
Date Issued
2018
Author(s)
Abstract
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 a 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 encoderdecoder 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 systems1. ? 2018 Association for Computational Linguistics.
Subjects
Computational linguistics; Decoding; Recurrent neural networks; Signal encoding; Speech processing; Critical component; Encoder-decoder; Encoder-decoder architecture; Linguistic patterns; Natural language generation; Recurrent neural network (RNN); Sentence structures; Spoken dialogue system; Natural language processing systems
Type
conference paper