arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.13006cs.CLcs.AI
收藏

自动FAQ生成

Auto FAQ Generation

California Polytechnic State University(加州州立理工大学)

Anjaneya Teja Kalvakolanu, NagaSai Chandra, Michael Fekadu

AI总结:

提出自动从大型文本中生成FAQ的系统,结合摘要、TextRank排序和问题生成,并用启发式过滤,人工评估显示71%的问题有意义。

摘要:

FAQ文档通常与文本文档和网站一起使用,以问答对的形式提供重要信息,既有助于阅读理解,也为关键思想提供快捷方式。我们假设给定文档中的显著句子可以作为读者聚合FAQ集合答案的良好代理。我们提出了一个生成FAQ文档的系统,该系统从斯坦福哲学百科全书中抓取的大型文本文档中提取显著问题及其对应答案。我们使用现有的文本摘要、通过TextRank算法进行句子排序以及问题生成工具来创建初始的问题和答案集。最后,我们应用一些启发式方法来过滤无效问题。我们使用人工评估来对生成的问题进行评分,评估其语法、问题是否有意义,以及问题的可回答性是否存在于摘要上下文中。平均而言,参与者认为71%的问题是有意义的。

英文摘要:

FAQ documents are commonly used with text documents and websites to provide important information in the form of question answer pairs to either aid in reading comprehension or provide a shortcut to the key ideas. We suppose that salient sentences from a given document serve as a good proxy fro the answers to an aggregated set of FAQs from readers. We propose a system for generating FAQ documents that extract the salient questions and their corresponding answers from sizeable text documents scraped from the Stanford Encyclopedia of Philosophy. We use existing text summarization, sentence ranking via the Text rank algorithm, and question-generation tools to create an initial set of questions and answers. Finally, we apply some heuristics to filter out invalid questions. We use human evaluation to rate the generated questions on grammar, whether the question is meaningful, and whether the question's answerability is present within a summarized context. On average, participants thought 71 percent of the questions were meaningful.

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。

↑