ABSTRACT
In e-commerce portals, generating answers for product-related questions has become a crucial task. In this paper, we propose the task of product-aware answer generation, which tends to generate an accurate and complete answer from large-scale unlabeled e-commerce reviews and product attributes. Unlike existing question-answering problems, answer generation in e-commerce confronts three main challenges: (1) Reviews are informal and noisy; (2) joint modeling of reviews and key-value product attributes is challenging; (3) traditional methods easily generate meaningless answers. To tackle above challenges, we propose an adversarial learning based model, named PAAG, which is composed of three components: a question-aware review representation module, a key-value memory network encoding attributes, and a recurrent neural network as a sequence generator. Specifically, we employ a convolutional discriminator to distinguish whether our generated answer matches the facts. To extract the salience part of reviews, an attention-based review reader is proposed to capture the most relevant words given the question. Conducted on a large-scale real-world e-commerce dataset, our extensive experiments verify the effectiveness of each module in our proposed model. Moreover, our experiments show that our model achieves the state-of-the-art performance in terms of both automatic metrics and human evaluations.
- Mart'in Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et almbox. 2016. Tensorflow: a system for large-scale machine learning.. In OSDI, Vol. 16. 265--283. Google ScholarDigital Library
- Martín Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein GAN. CoRR, Vol. abs/1701.07875 (2017).Google Scholar
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In ICLR .Google Scholar
- Lei Cui, Shaohan Huang, Furu Wei, Chuanqi Tan, Chaoqun Duan, and Ming Zhou. 2017. SuperAgent: A Customer Service Chatbot for E-commerce Websites. In ACL .Google Scholar
- John C. Duchi, Elad Hazan, and Yoram Singer. 2010. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. Journal of Machine Learning Research, Vol. 12 (2010), 2121--2159. Google ScholarDigital Library
- Gabriel Forgues, Joelle Pineau, Jean-Marie Larchevêque, and Réal Tremblay. 2014. Bootstrapping dialog systems with word embeddings. In Nips, modern machine learning and natural language processing workshop, Vol. 2.Google Scholar
- Jiatao Gu, Zhengdong Lu, Hang Li, and Victor O. K. Li. 2016. Incorporating Copying Mechanism in Sequence-to-Sequence Learning. In ACL .Google Scholar
- Ishaan Gulrajani, Faruk Ahmed, Martín Arjovsky, Vincent Dumoulin, and Aaron C. Courville. 2017. Improved Training of Wasserstein GANs. In NIPS . Google ScholarDigital Library
- Johan Hasselqvist, Niklas Helmertz, and Mikael Kågeb"ack. 2017. Query-Based Abstractive Summarization Using Neural Networks. CoRR, Vol. abs/1712.06100 (2017).Google Scholar
- Shizhu He, Cao Liu, Kang Liu, and Jun Zhao. 2017. Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning. In ACL .Google Scholar
- ZhenWang Jia, chen Liu, Xinyan Xiao, Yajuan Lyu, and Tian Wu. 2018. Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension. In ACL .Google Scholar
- Nal Kalchbrenner, Edward Grefenstette, and Phil Blunsom. 2014. A Convolutional Neural Network for Modelling Sentences. In ACL .Google Scholar
- Julian McAuley and Alex Yang. 2016. Addressing Complex and Subjective Product-Related Queries with Customer Reviews. In WWW (WWW '16). International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland, 625--635. Google ScholarDigital Library
- Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016a. Key-Value Memory Networks for Directly Reading Documents. In EMNLP . 1400--1409.Google Scholar
- Alexander H. Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016b. Key-Value Memory Networks for Directly Reading Documents. In EMNLP .Google Scholar
- Rajarshee Mitra. 2017. An Abstractive approach to Question Answering. arXiv preprint arXiv:1711.06238 (2017).Google Scholar
- Samaneh Moghaddam and Martin Ester. 2011. AQA: Aspect-based Opinion Question Answering. (2011), 89--96. Google ScholarDigital Library
- Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. CoRR, Vol. abs/1611.09268 (2016).Google Scholar
- Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In ACL . Google ScholarDigital Library
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100, 000Google Scholar
- Questions for Machine Comprehension of Text. In EMNLP .Google Scholar
- Alexander M. Rush, Sumit Chopra, and Jason Weston. 2015. A Neural Attention Model for Abstractive Sentence Summarization. In EMNLP .Google Scholar
- Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get To The Point: Summarization with Pointer-Generator Networks. In ACL .Google Scholar
- Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hananneh Hajishirzi. 2017. Bi-directional attention flow for machine comprehension. In ICLR .Google Scholar
- Iulian Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron C. Courville, and Yoshua Bengio. 2017. A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues. In AAAI . Google ScholarDigital Library
- Hongya Song, Zhaochun Ren, Shangsong Liang, Piji Li, Jun Ma, and Maarten de Rijke. 2017. Summarizing Answers in Non-Factoid Community Question-Answering. In Proceedings of the Tenth ACM International Conference on Web Search and Data Mining (WSDM '17). ACM, New York, NY, USA, 405--414. Google ScholarDigital Library
- Amanda Stent, Matthew Marge, and Mohit Singhai. 2005. Evaluating Evaluation Methods for Generation in the Presence of Variation. In CICLing .Google Scholar
- Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, and Rob Fergus. 2015. End-To-End Memory Networks. In NIPS . Google ScholarDigital Library
- Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to Sequence Learning with Neural Networks. In NIPS . Google ScholarDigital Library
- Chuanqi Tan, Furu Wei, Nan Yang, Bowen Du, Weifeng Lv, and Ming Zhou. 2018. S-Net: From Answer Extraction to Answer Synthesis for Machine Reading Comprehension. In AAAI .Google Scholar
- Chongyang Tao, Shen Gao, Mingyue Shang, Wei Wu, Dongyan Zhao, and Rui Yan. 2018a. Get The Point of My Utterance! Learning Towards Effective Responses with Multi-Head Attention Mechanism. In IJCAI. 4418--4424. Google ScholarDigital Library
- Chongyang Tao, Lili Mou, Dongyan Zhao, and Rui Yan. 2018b. RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems. In AAAI .Google Scholar
- Zhaopeng Tu, Yang Liu, Shuming Shi, and Tong Zhang. 2018. Learning to Remember Translation History with a Continuous Cache. TACL (2018).Google Scholar
- Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. In NIPS. 2692--2700. Google ScholarDigital Library
- Wenhui Wang, Nan Yang, Furu Wei, Baobao Chang, and Ming Zhou. 2017. Gated self-matching networks for reading comprehension and question answering. In ACL, Vol. 1. 189--198.Google Scholar
- Zhen Xu, Bingquan Liu, Baoxun Wang, Chengjie Sun, Xiaolong Wang, Zhuoran Wang, and Chao Qi. 2017. Neural Response Generation via GAN with an Approximate Embedding Layer. In EMNLP .Google Scholar
- Lili Yao, Yaoyuan Zhang, Yansong Feng, Dongyan Zhao, and Rui Yan. 2017. Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems. In EMNLP .Google Scholar
- Adams Wei Yu, David Dohan, Quoc Le, Thang Luong, Rui Zhao, and Kai Chen. 2018a. Fast and Accurate Reading Comprehension by Combining Self-Attention and Convolution. In ICLR .Google Scholar
- Jianfei Yu, Minghui Qiu, Jing Jiang, Jun Huang, Shuangyong Song, Wei Chu, and Haiqing Chen. 2018b. Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce. In WSDM . Google ScholarDigital Library
- Jianxing Yu, Zheng-Jun Zha, and Tat-Seng Chua. 2012. Answering opinion questions on products by exploiting hierarchical organization of consumer reviews. In EMNLP. 391--401. Google ScholarDigital Library
- Qian Yu and Wai Lam. 2018. Aware Answer Prediction for Product-Related Questions Incorporating Aspects. In WSDM. ACM, 691--699. Google ScholarDigital Library
Index Terms
- Product-Aware Answer Generation in E-Commerce Question-Answering
Recommendations
Multi-Type Textual Reasoning for Product-Aware Answer Generation
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalBy reading reviews and product attributes, e-commerce question-answering task aims to automatically generate natural-sounding answers for product-related questions. Existing methods, however, typically assume that each review and each product attribute ...
Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce
CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge ManagementProduct-related question answering (QA) is an important but challenging task in E-Commerce. It leads to a great demand on automatic review-driven QA, which aims at providing instant responses towards user-posted questions based on diverse product ...
Answer Ranking for Product-Related Questions via Multiple Semantic Relations Modeling
SIGIR '20: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information RetrievalMany E-commerce sites now offer product-specific question answering platforms for users to communicate with each other by posting and answering questions during online shopping. However, the multiple answers provided by ordinary users usually vary ...
Comments