Generating long and informative reviews with aspect-aware coarse-to-fine decoding

20Citations
Citations of this article
151Readers
Mendeley users who have this article in their library.

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.

References Powered by Scopus

Long Short-Term Memory

76974Citations
N/AReaders
Get full text

Learning phrase representations using RNN encoder-decoder for statistical machine translation

11651Citations
N/AReaders
Get full text

Bidirectional recurrent neural networks

7370Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Pretrained Language Models for Text Generation: A Survey

57Citations
N/AReaders
Get full text

Evaluating the evaluation of diversity in natural language generation

34Citations
N/AReaders
Get full text

Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network

27Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Li, J., Zhao, W. X., Wen, J. R., & Song, Y. (2020). Generating long and informative reviews with aspect-aware coarse-to-fine decoding. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 1969–1979). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p19-1190

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 61

80%

Researcher 10

13%

Professor / Associate Prof. 3

4%

Lecturer / Post doc 2

3%

Readers' Discipline

Tooltip

Computer Science 74

86%

Linguistics 6

7%

Engineering 3

3%

Business, Management and Accounting 3

3%

Save time finding and organizing research with Mendeley

Sign up for free