This paper presents an approach for the source retrieval task using two distinct keyphrase extraction strategies, namely n-grams from chunked text and named entities. The proposed approach was evaluated on TIRA and performed well against other participants of PAN CLEF.
Download PDF from the Institute for Systems Analysis of the Russian Academy of Sciences website: http://www.isa.ru/aidt/images/documents/2016-03/44_47.pdf
PDF at the Artificial Intelligence and Decision Making magazine website: http://www.aidt.ru/images/documents/2016-03/44_47.pdf
Download PDF from eLibrary (registration required): https://www.elibrary.ru/item.asp?id=27180834
I. V. Sochenkov, R. Maluleka. Query Formulation for Source Retrieval based on Named Entities and N-grams Extraction // Искусственный интеллект и принятие решений. 2016. №3. с. 44-47