Abstract
The search of information in large text repositories has been plagued by the so-called document-query vocabulary gap, i.e. the semantic discordance between the contents in the stored document entities on the one hand and the human query on the other hand. Over the past two decades, a significant body of works has advanced technical retrieval prowess while several studies have shed light on issues pertaining to human search behavior. We believe that these efforts should be conjoined, in the sense that automated retrieval systems have to fully emulate human search behavior and thus consider the procedure according to which users incrementally enhance their initial query. To this end, cognitive reformulation patterns that mimic user search behaviour are highlighted and enhancement terms which are statistically collocated with or lexical-semantically related to the original terms adopted in the retrieval process. We formalize the application of these patterns by considering a query conceptual representation and introducing a set of operations allowing to operate modifications on the initial query. A genetic algorithm-based weighting process allows placing emphasis on terms according to their conceptual role-type. An experimental evaluation on real-world datasets against relevance, language, conceptual and knowledge-based models is conducted. We also show, when compared to language and relevance models, a better performance in terms of mean average precision than a word embedding-based model instantiation.
Abstract (translated)
URL
https://arxiv.org/abs/2004.10035
