Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Tillmann Dönicke"'
Autor:
Luisa Gödeke, Florian Barth, Tillmann Dönicke, Hanna Varachkina, Anna Mareike Weimer, Benjamin Gittel, Anke Holler, Caroline Sporleder
Publikováno v:
Zeitschrift für digitale Geisteswissenschaften, Iss 10 (2022)
Generalisations in narrative texts typically do not or not exclusively serve to devise the narrated world, but provide information about the narrative instance, the meaning of what is told or the real world. The paper contributes to the linguistic
Externí odkaz:
https://doaj.org/article/c4c94309a965420b98ad3c87974700a2
Autor:
Tillmann Dönicke, Hanna Varachkina, Anna Mareike Weimer, Luisa Gödeke, Florian Barth, Benjamin Gittel, Anke Holler, Caroline Sporleder
Publikováno v:
Frontiers in Artificial Intelligence, Vol 4 (2022)
Literary narratives regularly contain passages that different readers attribute to different speakers: a character, the narrator, or the author. Since literary narratives are highly ambiguous constructs, it is often impossible to decide between diver
Externí odkaz:
https://doaj.org/article/e1d7e1a064484b2b915f73bd80d74dcd
Autor:
Anna Mareike Weimer, Florian Barth, Tillmann Dönicke, Luisa Gödeke, Hanna Varachkina, Anke Holler, Caroline Sporleder, Benjamin Gittel
This paper explores how both annotation procedures and automatic detection (i.e. classifiers) can be used to assess the consistency of textual literary concepts. We developed an annotation tagset for the "literary comment"—a frequently used but rar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::88772d4bc08ba33563c5208415aed0fb
Autor:
Tillmann Dönicke
Publikováno v:
Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021).
Publikováno v:
W-NUT@EMNLP
In this system paper, we present a transformer-based approach to the detection of informativeness in English tweets on the topic of the current COVID-19 pandemic. Our models distinguish informative tweets, i.e. tweets containing statistics on recover
Publikováno v:
COLING
This paper proposes a framework for the expression of typological statements which uses real-valued logics to capture the empirical truth value (truth degree) of a formula on a given data source, e.g. a collection of multilingual treebanks with compa