Towards Automatic Generation of Product Reviews from Aspect-Sentiment Scores

Hongyu Zang, Xiaojun Wan


Abstract
Data-to-text generation is very essential and important in machine writing applications. The recent deep learning models, like Recurrent Neural Networks (RNNs), have shown a bright future for relevant text generation tasks. However, rare work has been done for automatic generation of long reviews from user opinions. In this paper, we introduce a deep neural network model to generate long Chinese reviews from aspect-sentiment scores representing users’ opinions. We conduct our study within the framework of encoder-decoder networks, and we propose a hierarchical structure with aligned attention in the Long-Short Term Memory (LSTM) decoder. Experiments show that our model outperforms retrieval based baseline methods, and also beats the sequential generation models in qualitative evaluations.
Anthology ID:
W17-3526
Volume:
Proceedings of the 10th International Conference on Natural Language Generation
Month:
September
Year:
2017
Address:
Santiago de Compostela, Spain
Editors:
Jose M. Alonso, Alberto Bugarín, Ehud Reiter
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
168–177
Language:
URL:
https://aclanthology.org/W17-3526
DOI:
10.18653/v1/W17-3526
Bibkey:
Cite (ACL):
Hongyu Zang and Xiaojun Wan. 2017. Towards Automatic Generation of Product Reviews from Aspect-Sentiment Scores. In Proceedings of the 10th International Conference on Natural Language Generation, pages 168–177, Santiago de Compostela, Spain. Association for Computational Linguistics.
Cite (Informal):
Towards Automatic Generation of Product Reviews from Aspect-Sentiment Scores (Zang & Wan, INLG 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/W17-3526.pdf