Programm 72. StuTS

DURel is an annotation tool for sentence pairs of a word. The annotations are used to form sense clusters of a word and to visualize them over time.
The web application has been used by a variety of different research projects focusing on the comparison and/or discovery of word senses and is currently being improved in regard to usability and utility, e.g. in order to adapt the tool for practical lexicographic purposes.
DURel provides an annotation interface for sentence pairs of a word. Annotators are asked to judge the degree of semantic relatedness of pairs of word uses. One example would be the two uses of arm in (1) and (2) on a scale of 1 (unrelated) to 4 (identical).
(1) and taking a knife from her pocket, she opened a vein in her little arm, and dipping a feather in the blood, wrote something on a piece of white cloth, which was spread before her.
(2) It stood behind a high brick wall, its back windows overlooking an arm of the sea which, at low tide, was a black and stinking mud-flat
The annotated data of a word is then represented in a Word Usage Graph (WUG). Its nodes represent word uses and weights on edges represent the (median) semantic relatedness judgment of a pair of uses as e.g. (1) and (2).
The focus of our talk will be on improvements being made in DURel, so that researchers can utilize information from clustering to explain semantic change or annotate word usages.
Users may use the tool to manage their projects, assigning them to registered annotators. For annotations so far, the data used has been extracted from time-specific historical subcorpora for each language (e.g. English, German, Swedish, Latin). The user's annotation can be stopped at any point and the finished data can be downloaded. The system also allows to directly cluster and visualize the data over time as interactive WUGs. New functionalities include the ability to switch between clustering and dimension reduction methods. This could lead to better results depending on each annotator's area of focus.
Additionally, a user study will be conducted with the goal of evaluating improvements in the tool's interface for linguistics researchers and lexicographers interested in word usage changes over time.

Info

Tag: 03.11.2022
Anfangszeit: 14:15
Dauer: 00:30
Raum: Wiwi-Bunker —Room 5050
Track: Computational Linguistics
Sprache: en

Links:

• iCalendar

Feedback

Uns interessiert Ihre Meinung! Wie fanden Sie diese Veranstaltung?