电子商务中基于多信息源的问题回答生成
Answer Generation for Questions With Multiple Information Sources in E-Commerce
AI总结：
本文提出了一种新颖的流程（MSQAP），通过分别进行相关性和歧义预测来利用评论、相似问题和规格说明等多信息源，从而在电子商务中生成更准确的答案。
摘要：
自动问答是电子商务中一项重要且具有挑战性的任务，因为用户会针对他们有意购买的产品发布数以百万计的问题。因此，对利用产品相关信息提供快速响应的自动答案生成系统存在巨大需求。回答用户发布的查询有三个可用的知识来源，即评论、重复或相似的问题以及规格说明。有效利用这些信息源将极大地帮助我们回答复杂问题。然而，在利用这些来源时存在两个主要挑战：(i) 无关信息的存在，以及 (ii) 评论和相似问题中存在的情感歧义。通过这项工作，我们提出了一种新颖的流程（MSQAP），通过在生成响应之前分别进行相关性和歧义预测，来利用上述来源中存在的丰富信息。实验结果表明，我们的相关性预测模型（BERT-QA）优于所有其他变体，与BERT-base基线相比，F1分数提高了12.36%。我们的生成模型（T5-QA）在所有内容保留指标（如BLEU、ROUGE）上均优于基线，与表现最高的基线（HSSC-q）相比，ROUGE平均提高了35.02%，BLEU提高了198.75%。对我们流程的人工评估表明，与生成模型（T5-QA）相比，我们的方法在准确率上总体提高了30.7%，从而使我们基于完整流程的方法（MSQAP）能够提供更准确的答案。据我们所知，这是电子商务领域中首个结合规格说明、相似问题和评论数据等多种来源中存在的信息，自动生成自然语言答案的工作。
英文摘要：
Automatic question answering is an important yet challenging task in E-commerce given the millions of questions posted by users about the product that they are interested in purchasing. Hence, there is a great demand for automatic answer generation systems that provide quick responses using related information about the product. There are three sources of knowledge available for answering a user posted query, they are reviews, duplicate or similar questions, and specifications. Effectively utilizing these information sources will greatly aid us in answering complex questions. However, there are two main challenges present in exploiting these sources: (i) The presence of irrelevant information and (ii) the presence of ambiguity of sentiment present in reviews and similar questions. Through this work we propose a novel pipeline (MSQAP) that utilizes the rich information present in the aforementioned sources by separately performing relevancy and ambiguity prediction before generating a response. Experimental results show that our relevancy prediction model (BERT-QA) outperforms all other variants and has an improvement of 12.36% in F1 score compared to the BERT-base baseline. Our generation model (T5-QA) outperforms the baselines in all content preservation metrics such as BLEU, ROUGE and has an average improvement of 35.02% in ROUGE and 198.75% in BLEU compared to the highest performing baseline (HSSC-q). Human evaluation of our pipeline shows us that our method has an overall improvement in accuracy of 30.7% over the generation model (T5-QA), resulting in our full pipeline-based approach (MSQAP) providing more accurate answers. To the best of our knowledge, this is the first work in the e-commerce domain that automatically generates natural language answers combining the information present in diverse sources such as specifications, similar questions, and reviews data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
