Paper: Learning Adaptable Patterns for Passage Reranking

ACL ID W13-3509
Title Learning Adaptable Patterns for Passage Reranking
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2013

This paper proposes passage reranking models that (i) do not require manual fea- ture engineering and (ii) greatly preserve accuracy, when changing application do- main. Their main characteristic is the use of relational semantic structures rep- resenting questions and their answer pas- sages. The relations are established us- ing information from automatic classifiers, i.e., question category (QC) and focus classifiers (FC) and Named Entity Recog- nizers (NER). This way (i) effective struc- tural relational patterns can be automati- cally learned with kernel machines; and (ii) structures are more invariant w.r.t. dif- ferent domains, thus fostering adaptability.