Exploring the Fuzzy Boundaries of Discourse Markers Through Manual and Automatic Annotation
Loading...
Date
2020
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Palgrave Macmillan Cham
Abstract
Discourse markers are non-propositional linguistic items that are notoriously
difficult to identify as well as to categorize. We can observe several borderline
phenomena and overlaps with other formal and functional categories, for
example inserts, adverbials, contextualization cues, pragmatic force modifiers
and so on. By way of addressing such overlaps as well as the disambiguation
between discourse marker uses and their source categories, the chapter presents
a comparison of automated and manual annotation of oral discourse markers
(discourse markers). Firstly, an overview of the criterial features of discourse
markers that are relevant to disambiguation is presented. Secondly, the UCREL
Semantic Analysis System (USAS) and its disambiguation methods are briefly
discussed. In the third part of the chapter manual and automatic decisions
about categorization are compared with a view to addressing the margin of
error reported to apply in general semantic annotation as well as the question
of what formal-functional properties of the relevant discourse markers might
explain possible differences between manual and automatic annotation.