Feature Generation for Text Categorization Using World Knowledge

By Evgeniy Gabrilovich, Shaul Markovitch. International Joint Conference on Artificial Intelligence, 2005

299 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c54f38857d25315ad1ca4024010cfd985d361e9b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

TAGME: on-the-fly annotation of short text fragments (by wikipedia entities) (2010, methodology): “For the experiments we split each iitb document into fragments of 30 words each, so to obtain a short input text (mimicking the snippet of a search-engine result).”
Computing Semantic Relatedness Using Wikipedia-based Explicit Semantic Analysis (2007, methodology): “Further implementation details are available in [Gabrilovich and Markovitch, 2005].”
Just-in-time contextual advertising (2007, methodology): “Following [11], we constructed additional features based on these immediate classifications as well as their ancestors in the taxonomy (the weight of each ancestor feature was decreased with a damping factor of 0.”
Overcoming the Brittleness Bottleneck using Wikipedia: Enhancing Text Categorization with Encyclopedic Knowledge (2006, methodology): “Wikipedia as a Knowledge Repository What kind of knowledge repository should be used for feature generation? In our earlier work ( Gabrilovich & Markovitch 2005 ), we assumed the external knowledge is available in the form of a generalization hierarchy, and used the Open Directory Project (ODP,www.d”
Importance of Semantic Representation: Dataless Classification (2008, unknown): “ESA representations into a single BOW+ESA view as was done in ( Gabrilovich & Markovitch 2005 ) for supervised classification.”
Strengthening learning algorithms by feature discovery (2012, methodology): “Constructive induction is used in various new machine learning classifiers, including genetic algorithms [14,20], multivariate time series classifiers [10], rule induction algorithm for variable consistency rough set approaches [1] and feature generation for text categorization [6].”
Fast and Accurate Annotation of Short Texts with Wikipedia Pages (2010, background): “One approach consists of extending the classic term-based vector-space model with additional dimensions corresponding to features (concepts) extracted from an external knowledge base, such as DMOZ [4, 6], Wikipedia [7, 1, 9], or even the whole Web (such as the Google’s kernel [15]).”
Concept-Based Information Retrieval Using Explicit Semantic Analysis (2011, methodology): “The use of ODP as a source for concept representation and automatic mapping has some parallels with our ESA approach, in particular when considering that ESA was implemented over ODP data as well [Gabrilovich and Markovitch 2005].”