Dr. Tux: A Question Answering System for Ubuntu users
This addresses a specific problem for Ubuntu users by automating question retrieval, but it is incremental as it applies existing NLP tools to a new dataset.
The authors tackled the problem of time-consuming search for Ubuntu-related questions by developing Dr. Tux, an automated question answering system that selects the most similar question from an online database, with promising results from manual evaluation on 150k questions from AskUbuntu.
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.