transparent gif


Ej inloggad.

Göteborgs universitets publikationer

Towards Using Reranking in Hierarchical Classification

Författare och institution:
Qi Ju (-); Richard Johansson (Institutionen för svenska språket); Alessandro Moschitti (-)
Publicerad i:
Proceedings of the Joint ECML/PKDD-PASCAL Workshop on Large-Scale Hierarchical Classification; September 5, 2011; Athens, Greece,
Konferensbidrag, refereegranskat
Sammanfattning (abstract):
We consider the use of reranking as a way to relax typical in- dependence assumptions often made in hierarchical multilabel classification. Our reranker is based on (i) an algorithm that generates promising k-best classification hypotheses from the output of local binary classifiers that clas- sify nodes of a target tree-shaped hierarchy; and (ii) a tree kernel-based reranker applied to the classification tree associated with the hypotheses above. We carried out a number of experiments with this model on the Reuters corpus: we firstly show the potential of our algorithm by computing the oracle classification accuracy. This demonstrates that there is a signifi- cant room for potential improvement of the hierarchical classifier. Then, we measured the accuracy achieved by the reranker, which shows a significant performance improvement over the baseline.
Ämne (baseras på Högskoleverkets indelning av forskningsämnen):
Data- och informationsvetenskap ->
Språkteknologi (språkvetenskaplig databehandling)
Data- och informationsvetenskap ->
Annan data- och informationsvetenskap ->
Övrig informationsteknik
datorlingvistik, språkteknologi, textkategorisering, maskininlärning
Postens nummer:
Posten skapad:
2012-01-02 10:34
Posten ändrad:
2012-04-03 11:34

Visa i Endnote-format

Göteborgs universitet • Tel. 031-786 0000
© Göteborgs universitet 2007