Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding
TL
TL;DR
A novel review generation model is proposed by characterizing an elaborately designed aspect-aware coarse-to-fine generation process that is able to jointly utilize aspect semantics, syntactic sketch, and context information.
Abstract
Generating long and informative review text is a challenging natural language generation task. Previous work focuses on word-level generation, neglecting the importance of topical and syntactic characteristics from natural languages. In this paper, we propose a novel review generation model by characterizing an elaborately designed aspect-aware coarse-to-fine generation process. First, we model the aspect transitions to capture the overall content flow. Then, to generate a sentence, an aspect-aware sketch will be predicted using an aspect-aware decoder. Finally, another decoder fills in the semantic slots by generating corresponding words. Our approach is able to jointly utilize aspect semantics, syntactic sketch, and context information. Extensive experiments results have demonstrated the effectiveness of the proposed model.
References38 items
1
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
2
A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
3
Learning Neural Templates for Text Generation
4
Personalized Review Generation By Expanding Phrases and Attending on Aspect-Aware Representations
5