arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.11768cs.CLcs.LG
收藏

使用BERT的会话系统的产品标题生成

Product Title Generation for Conversational Systems using BERT

Walmart Labs(沃尔玛实验室)

Mansi Ranjit Mane, Shashank Kedia, Aditya Mantha, Stephen Guo, Kannan Achan

摘要:

通过语音技术的最新进步和智能设备的引入,例如Amazon Alexa和Google Home,越来越多的用户通过语音与应用程序进行交互。电子商务公司通常在其网页上显示简短的产品标题,无论是人工策划还是算法生成,当需要简洁时,但这些标题与自然口语不同。例如,“Lucky Charms Gluten Free Break-fast Cereal,20.5盎司一盒Lucky Charms Gluten Free”可以在网页上显示,但“20.5盎司一盒Lucky Charms Gluten Free Cereal”在对话系统上更容易理解。与可以向用户呈现图像和详细产品信息的显示器相比,当与语音助理交互时,产品的简短标题是必要的。我们提出了一个序列到序列的方法,使用BERT生成短,自然,口语标题从输入的Web标题。我们在真实世界的行业数据集上进行的大量实验和对模型输出的人工评估表明,BERT摘要优于可比的基线模型。

英文摘要:

Through recent advancements in speech technology and introduction of smart devices, such as Amazon Alexa and Google Home, increasing number of users are interacting with applications through voice. E-commerce companies typically display short product titles on their webpages, either human-curated or algorithmically generated, when brevity is required, but these titles are dissimilar from natural spoken language. For example, "Lucky Charms Gluten Free Break-fast Cereal, 20.5 oz a box Lucky Charms Gluten Free" is acceptable to display on a webpage, but "a 20.5 ounce box of lucky charms gluten free cereal" is easier to comprehend over a conversational system. As compared to display devices, where images and detailed product information can be presented to users, short titles for products are necessary when interfacing with voice assistants. We propose a sequence-to-sequence approach using BERT to generate short, natural, spoken language titles from input web titles. Our extensive experiments on a real-world industry dataset and human evaluation of model outputs, demonstrate that BERT summarization outperforms comparable baseline models.

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。

↑