[Zurück]

N. Rekabsaz:
"Enhancing Information Retrieval with Adapted Word Embedding";
Vortrag: the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, Pisa; 17.06.2016 - 21.06.2016; in: "Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval", ACM, New York, NY, USA ©2016 (2016), ISBN: 978-1-4503-4069-4; S. 1169.

Recent developments on word embedding provide a novel source of information for term-to-term similarity. A recurring question now is whether the provided term associations can be properly integrated in the traditional information retrieval models while preserving their robustness and effectiveness. In this paper, we propose addressing the question of combining the term-to-term similarity of word embedding with IR models. The retrieval models in the approach are enhanced by altering the basic components of document retrieval, i.e. term frequency (tf ) and document frequency (df ). In addition, we target the study of the meaning of the term relatedness of word embedding models and its applicability in IR. This research topic consists of first explore of reliable similarity thresholds of word embedding vectors to indicate "related terms" and second, identification of the linguistic types of the terms relatedness.

IR Models; word embeddings; similarity; related terms

http://dx.doi.org/10.1145/2911451.2911475