arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.08097cs.CL
收藏

大规模自然语言生成:开放领域问答的案例研究

Natural Language Generation at Scale: A Case Study for Open Domain Question Answering

University of Trento(特伦托大学);Amazon Alexa AI(亚马逊Alexa人工智能);Uber AI(优步人工智能);Google(谷歌)

Alessandra Cervone, Chandra Khatri, Rahul Goel, Behnam Hedayatnia, Anu Venkatesh, Dilek Hakkani-Tur, Raefer Gabriel

摘要:

当前的对话自然语言生成(NLG)方法主要集中在使用有限本体(多达20种槽类型)的特定于域的面向任务的应用(例如,餐厅预订),通常不考虑先前的对话上下文。此外,这些方法需要每个域的大量数据,并且不能受益于可用于其他域的示例。这项工作探讨了将统计NLG应用于需要更大本体的场景的可行性,例如基于知识图谱的多域对话应用或开放域问答(QA)。我们通过一个编码器-解码器框架,使用一个大的数据集的真实世界的用户和开放域QA的会话代理之间的交互NLG模型。首先,我们调查的影响,增加插槽类型的数量上的生成质量和实验的QA数据的不同分区与逐渐增大的本体(高达369插槽类型)。其次,我们在开放域QA和面向任务的对话之间进行多任务学习实验,并在流行的NLG数据集上对我们的模型进行基准测试。此外,我们尝试使用会话上下文作为额外的输入,以提高响应生成质量。我们的实验表明,学习统计NLG模型的开放域QA与较大的本体的可行性。

英文摘要:

Current approaches to Natural Language Generation (NLG) for dialog mainly focus on domain-specific, task-oriented applications (e.g. restaurant booking) using limited ontologies (up to 20 slot types), usually without considering the previous conversation context. Furthermore, these approaches require large amounts of data for each domain, and do not benefit from examples that may be available for other domains. This work explores the feasibility of applying statistical NLG to scenarios requiring larger ontologies, such as multi-domain dialog applications or open-domain question answering (QA) based on knowledge graphs. We model NLG through an Encoder-Decoder framework using a large dataset of interactions between real-world users and a conversational agent for open-domain QA. First, we investigate the impact of increasing the number of slot types on the generation quality and experiment with different partitions of the QA data with progressively larger ontologies (up to 369 slot types). Second, we perform multi-task learning experiments between open-domain QA and task-oriented dialog, and benchmark our model on a popular NLG dataset. Moreover, we experiment with using the conversational context as an additional input to improve response generation quality. Our experiments show the feasibility of learning statistical NLG models for open-domain QA with larger ontologies.

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。

↑