A distributional semantic methodology for enhanced search in historical records: A case study on smell

Conference Object
Change log
McGregor, S 
McGillivray, Barbara  ORCID logo  https://orcid.org/0000-0003-3426-8200

In this paper we present a methodology based on distributional semantic models that can be flexibly adapted to the specific challenges posed by historical texts and that allow users to retrieve semantically relevant text without the need to close-read the documents. We focus on a case study concerned with detecting smell-related sentences in historical medical reports. We demonstrate a process for moving from generic domain label input to a more nuanced evaluation of the semantics of smell in a set of sentences extracted from this corpus, and then develop a machine learning technique for compounding scores on a variety of modelling parameters into more effective classifications.

Journal Title
KONVENS 2018 - Conference on Natural Language Processing / Die Konferenz zur Verarbeitung Naturlicher Sprache
Conference Name
14th Conference on Natural Language Processing (KONVENS 2018)
Journal ISSN
Volume Title
Austrian Academy of Sciences Press
Alan Turing Institute (EP/N510129/1)
This work was supported by the Chist-ERA Atlantis project. This work was supported by The Alan Turing Institute under the EPSRC grant EP/N510129/1.