Handling Information Overload: Automatic Generation of Wikipedia Articles

From Wikipedia Quality
Jump to: navigation, search


Handling Information Overload: Automatic Generation of Wikipedia Articles
Authors
Vikrant Yadav
Faisal Khan
Publication date
2015
Links
Original

Handling Information Overload: Automatic Generation of Wikipedia Articles - scientific work related to Wikipedia quality published in 2015, written by Vikrant Yadav and Faisal Khan.

Overview

The exponential growth of information on the web over the years has lead to the problem of information overload, i.e. amount of information present on web is beyond the processing capacity of any system. Thus, a need arises to have a single resource to properly cover as well as to have an up to date information about a topic. The popular website Wikipedia does the same in a structured manner thus giving a comprehensive coverage about any topic. However, Wikipedia is crowdsourced and thus can’t cover everything. So, a mechanism is required which takes large number of documents from the web and gives a Wikipedia like structured and detailed information about any topic in real-time. For automatic generation of such an article, a structure-aware approach has been proposed by Sauper et. al. (2009) [2]. They generated templates for different categories and for a given topic, retrieved information from the web using pre-learned queries. However, their approach lacks to utilize semantic relationships between the information under similar sections in different articles. Instead of just clustering section titles to generate templates and queries, study suggests that a topic model like Replicated Softmax [1] or Deep Boltzmann Machines [3] can be used to create better templates and queries. Also, authors generate semantically similar queries for each pre-learned query using DBPedia and the results are then combinedly re-ranked using algorithm. This results in high-quality information from web and a coherent and comprehensive article. BODY Semantic relationships among existing Wikipedia articles can be used to generate high-quality structured information on a given topic.

Embed

Wikipedia Quality

Yadav, Vikrant; Khan, Faisal. (2015). "[[Handling Information Overload: Automatic Generation of Wikipedia Articles]]".

English Wikipedia

{{cite journal |last1=Yadav |first1=Vikrant |last2=Khan |first2=Faisal |title=Handling Information Overload: Automatic Generation of Wikipedia Articles |date=2015 |url=https://wikipediaquality.com/wiki/Handling_Information_Overload:_Automatic_Generation_of_Wikipedia_Articles}}

HTML

Yadav, Vikrant; Khan, Faisal. (2015). &quot;<a href="https://wikipediaquality.com/wiki/Handling_Information_Overload:_Automatic_Generation_of_Wikipedia_Articles">Handling Information Overload: Automatic Generation of Wikipedia Articles</a>&quot;.