Nikolaev Fedor Aleksandrovich (архив)
Николаев Федор Александрович
- Short description of important scientific result: Accurate projection of terms in free-text queries onto structured entity representations is one of the fundamental problems in entity retrieval from knowledge graphs. We demonstrated that existing retrieval models for ad-hoc structured and unstructured document retrieval fall short of addressing this problem, due to their rigid assumptions. According to these assumptions, either all query concepts of the same type are projected onto the fields of entity representations with identical weights or such projection is determined based only on one simple statistic, which makes it sensitive to data sparsity. To address this issue, we proposed the Parametrized Fielded Sequential Dependence Model (PFSDM) and the Parametrized Fielded Full Dependence Model (PFFDM), two novel models for entity retrieval from knowledge graphs, which infer the user's intent behind each individual query concept by dynamically estimating its projection onto the structured fields. Coauthors: Kotov, A., Zhiltsov, N.
- Unique identifier in the Web of Science (Researcher ID): http://www.researcherid.com/rid/C-7745-2015
- Unique identifier in the Scopus (Author ID): http://www.scopus.com/authid/detail.url?authorId=57044816700
- Quantity of published work in Scopus: 6
- Quantity of reference on published work in Scopus: 91
- Personal index of Hirsh: 3
- Unique identifier in the Elibrary (Author ID): http://elibrary.ru/author_items.asp?authorid=797115
- Unique identifier in the ORCID (ORCID ID): http://orcid.org/0000-0001-6343-1623
