{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/190501994","title":"Review-Driven Answer Generation for Product-Related Questions in E-Commerce","arxiv_id":"1905.01994","date":"2019-04-27","proceeding":null,"authors":["Shiqian Chen","Chenliang Li","Feng Ji","Wei Zhou","Haiqing Chen"],"abstract":"The users often have many product-related questions before they make a\npurchase decision in E-commerce. However, it is often time-consuming to examine\neach user review to identify the desired information. In this paper, we propose\na novel review-driven framework for answer generation for product-related\nquestions in E-commerce, named RAGE. We develope RAGE on the basis of the\nmulti-layer convolutional architecture to facilitate speed-up of answer\ngeneration with the parallel computation. For each question, RAGE first\nextracts the relevant review snippets from the reviews of the corresponding\nproduct. Then, we devise a mechanism to identify the relevant information from\nthe noise-prone review snippets and incorporate this information to guide the\nanswer generation. The experiments on two real-world E-Commerce datasets show\nthat the proposed RAGE significantly outperforms the existing alternatives in\nproducing more accurate and informative answers in natural language. Moreover,\nRAGE takes much less time for both model training and answer generation than\nthe existing RNN based generation models.","url_abs":"http://arxiv.org/abs/1905.01994v1","url_pdf":"http://arxiv.org/pdf/1905.01994v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"190501994","repo_url":"https://github.com/WHUIR/RAGE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"answer-generation","task_name":"Answer Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.01994","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}