Resolving Surface Forms to Wikipedia Topics
Authors | Yiping Zhou Lan Nie Omid Rouhani-kalleh Flavian Vasile Scott Gaffney |
|---|---|
Publication date | 2010 |
Links | Original |
Resolving Surface Forms to Wikipedia Topics - scientific work related to Wikipedia quality published in 2010, written by Yiping Zhou, Lan Nie, Omid Rouhani-kalleh, Flavian Vasile and Scott Gaffney.
Overview
Ambiguity of entity mentions and concept references is a challenge to mining text beyond surface-level keywords. Authors describe an effective method of disambiguating surface forms and resolving them to Wikipedia entities and concepts. Authors method employs an extensive set of features mined from Wikipedia and other large data sources, and combines the features using a machine learning approach with automatically generated training data. Based on a manually labeled evaluation set containing over 1000 news articles, resolution model has 85% precision and 87.8% recall. The performance is significantly better than three baselines based on traditional context similarities or sense commonness measurements. Authors method can be applied to other languages and scales well to new entities and concepts.
Embed
Wikipedia Quality
Zhou, Yiping; Nie, Lan; Rouhani-kalleh, Omid; Vasile, Flavian; Gaffney, Scott. (2010). "[[Resolving Surface Forms to Wikipedia Topics]]". Association for Computational Linguistics.
English Wikipedia
{{cite journal |last1=Zhou |first1=Yiping |last2=Nie |first2=Lan |last3=Rouhani-kalleh |first3=Omid |last4=Vasile |first4=Flavian |last5=Gaffney |first5=Scott |title=Resolving Surface Forms to Wikipedia Topics |date=2010 |url=https://wikipediaquality.com/wiki/Resolving_Surface_Forms_to_Wikipedia_Topics |journal=Association for Computational Linguistics}}
HTML
Zhou, Yiping; Nie, Lan; Rouhani-kalleh, Omid; Vasile, Flavian; Gaffney, Scott. (2010). "<a href="https://wikipediaquality.com/wiki/Resolving_Surface_Forms_to_Wikipedia_Topics">Resolving Surface Forms to Wikipedia Topics</a>". Association for Computational Linguistics.
