Meaningful Answer Generation of E-Commerce Question-Answering
arXiv:2011.07307
Abstract
In e-commerce portals, generating answers for product-related questions has become a crucial task. In this paper, we focus on the task of product-aware answer generation, which learns to generate an accurate and complete answer from large-scale unlabeled e-commerce reviews and product attributes. However, safe answer problems pose significant challenges to text generation tasks, and e-commerce question-answering task is no exception. To generate more meaningful answers, in this paper, we propose a novel generative neural model, called the Meaningful Product Answer Generator (MPAG), which alleviates the safe answer problem by taking product reviews, product attributes, and a prototype answer into consideration. Product reviews and product attributes are used to provide meaningful content, while the prototype answer can yield a more diverse answer pattern. To this end, we propose a novel answer generator with a review reasoning module and a prototype answer reader. Our key idea is to obtain the correct question-aware information from a large scale collection of reviews and learn how to write a coherent and meaningful answer from an existing prototype answer. To be more specific, we propose a read-and-write memory consisting of selective writing units to conduct reasoning among these reviews. We then employ a prototype reader consisting of comprehensive matching to extract the answer skeleton from the prototype answer. Finally, we propose an answer editor to generate the final answer by taking the question and the above parts as input. Conducted on a real-world dataset collected from an e-commerce platform, extensive experimental results show that our model achieves state-of-the-art performance in terms of both automatic metrics and human evaluations. Human evaluation also demonstrates that our model can consistently generate specific and proper answers.
Accepted By TOIS
References in corpus (19)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- A Deep Reinforced Model for Abstractive Summarization
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- End-To-End Memory Networks
- Topic Aware Neural Response Generation
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems
- Low-Resource Knowledge-Grounded Dialogue Generation
- S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
- Query-Based Abstractive Summarization Using Neural Networks
- Global Encoding for Abstractive Summarization
- Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
- Learning to Remember More with Less Memorization
- Response Generation by Context-aware Prototype Editing
- Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
- Concept Pointer Network for Abstractive Summarization
- Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog
- AmazonQA: A Review-Based Question Answering Task
- BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization