Various forums and question answering (Q&A) sites are available online that allow Ubuntu users to find results similar to their queries. However, searching for a result is often time consuming as it requires the user to find a specific problem instance relevant to his/her query from a large set of questions. In this paper, we present an automated question answering system for Ubuntu users called Dr. Tux that is designed to answer user's queries by selecting the most similar question from an online database. The prototype was implemented in Python and uses NLTK and CoreNLP tools for Natural Language Processing. The data for the prototype was taken from the AskUbuntu website which contains about 150k questions. The results obtained from the manual evaluation of the prototype were promising while also presenting some interesting opportunities for improvement.
翻译:各种论坛和问题解答网站(QAA)都在线提供,让Ubuntu用户能找到类似于其查询的结果。然而,寻找结果往往耗时费时,因为它要求用户从一大堆问题中找到与其查询相关的特定问题实例。在本文中,我们为Ubuntu用户提供了一个自动问答系统,称为Tux博士,目的是通过从网上数据库中选择最相似的问题回答用户的问题。原型在Python实施,并使用NLTK和CoreNLP工具进行自然语言处理。原型的数据取自AskUbuntu网站,该网站包含大约150公里的问题。对原型的手工评估的结果很有希望,同时也提供了一些有趣的改进机会。