Opponent, University of Helsinki

Honkela, T. (Vastaväittäjä)

Aktiviteetti: TutkimustyypitVastaväittäjä

Kuvaus

Department of Computer Science
Series of Publications A

Word Associations as a Language Model for Generative and Creative Tasks
Oskar Gross

Presented, with the permission of the Faculty of Science of the University of Helsinki, for public criticism in Auditorium XIV, University Main Building, on May 6th, 2016 at noon.
University of Helsinki
Finland

Supervisor
Hannu Toivonen, University of Helsinki, Finland

Pre-examiners
Tony Veale, University College Dublin, Ireland
Krista Lagus, University of Helsinki, Finland

Opponent
Timo Honkela, University of Helsinki, Finland

Custos
Hannu Toivonen, University of Helsinki, Finland

Copyright c 2016 Oskar Gross
ISSN 1238-8645
ISBN 978-951-51-2089-2 (paperback)
ISBN 978-951-51-2090-8 (PDF)

Abstract

In order to analyse natural language and gain a better understanding of documents, a common approach is to produce a language model which
creates a structured representation of language which could then be used
further for analysis or generation. This thesis will focus on a fairly simple
language model which looks at word associations which appear together
in the same sentence. We will revisit a classic idea of analysing word co-
occurrences statistically and propose a simple parameter-free method for
extracting common word associations, i.e. associations between words that
are often used in the same context (e.g., Batman and Robin). Additionally we propose a method for extracting associations which are speci c to a
document or a set of documents. The idea behind the method is to take into
account the common word associations and highlight such word associations
which co-occur in the document unexpectedly often. ...

Title of thesis: Word Associations as a Language Model for Generative and Creative Tasks
Aikajakso6 toukokuuta 2016
TutkittavaOskar Gross
Tutkimuksen ajankohtaUniversity of Helsinki