Elements of a Learning Interface for Genre Qualified Search

Stubbe, Andrea; Ringlstetter, Christoph; Goebel, Randy

doi:10.1007/978-3-540-76928-6_94

Cited by 5 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hierarchical organized schemata, as compared to flat lists, have the advantage that the granularity of classification can be adapted to the information task and that different levels of classification errors can be distinguished. An example for a hierarchical view on document genre is given with the branches for the high‐level genres journalism and literature as proposed in our genre hierarchy for web retrieval [1]: journalism container : commentary, review, marginal note, interview, portrait, news, feature, reportage literature container : poem, prose, drama …”

Section: Schema Of Genresmentioning

confidence: 99%

Bringing genre into focus: Practical aspects of automatic genre classification

Ringlstetter

Stubbe

2008

Bul. Am. Soc. Info. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

Section: Schema Of Genresmentioning

confidence: 99%

Bringing genre into focus: Practical aspects of automatic genre classification

Ringlstetter

Stubbe

2008

Bul. Am. Soc. Info. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

“…Experiments [24] have shown that though most users expect genre information to be helpful for their Web search tasks, a straightforward implementation of genre-related hints does not improve user search effectiveness significantly. Moreover users can recognize distinct genres (such as catalog, FAQ, blog, or news) with high accuracy even from ordinary snippets [30].…”

Section: Introductionmentioning

confidence: 99%

Marrying Relevance and Genre Rankings: An Exploratory Study

Braslavski

2010

Text, Speech and Language Technology

View full text Add to dashboard Cite

Summary. In this chapter, we discuss different options for using genre-related information in Web search. We conduct an experiment on merging genre-related and text-relevance rankings using a reference Web collection. A method for automatic extraction of formality score akin to readability score using canonical discriminant analysis applied to a sample of genres with decreasing formality is proposed. Effects of aggregating genre-related and text relevance rankings are considered. Evaluation of the results shows moderate positive effects. Findings suggest that further research is needed on implicit use of genre-related information in Web search.

show abstract