???Webpage.gotoContents???

Detailansicht

resarch data

Yordanova,  Kristina

Time series from textual instructions for causal relations discovery (Causal relations dataset)

Rostock :  Universität Rostock ,  2015

One aspect of ontology learning methods is the discovery of relations in textual data. One kind of such relations are causal relations. Our aim is to discover causations described in texts such as recipes and manuals. There is a lot of research on causal relations discovery that is based on grammatical patterns. These patterns are, however, rarely discovered in textual instructions (such as recipes) with short and simple sentence structure. Therefore we use time series to discover causal relations. To do that, each word of interest in the text is converted into time series that represent how often and in which time stamp this word appears in the text. Then a time series analysis can be applied to discover causal relations.

DOI:  10.18453/rosdok_id00000117

http://purl.uni-rostock.de/rosdok/id00000117

Daten:
D20150330-Causal_Relations-KY.zip
0.171 MB
MD5: 42a686e6e3e683894a4227c954787e03
Dokumentation:
documentation.pdf
0.172 MB
MD5: b4818d59e4a6738c4f8ffc87601bcb2c

Lizenz:
Creative Commons Lizenzvertrag
Dieses Werk ist lizenziert unter einer Creative Commons Namensnennung 4.0 International Lizenz.

Jahr der Erstellung:2015
Lokaler Identifikator:D20150330-Causal_Relations-KY
Typ:Measurement
Schlagworte:textual instructions
causal relations
time series
Publikationen:

Frank Krüger, Martin Nyolt, Kristina Yordanova, Albert Hein, and Thomas Kirste. Computational state space models for activity and intention recognition. a feasibility study. PLoS ONE, 9(11):e109381, 11 2014.
DOI:10.1371/journal.pone.0109381

Kristina Yordanova. Discovering causal relations in textual instructions. In Recent Advances in Natural Language Processing, Hissar, Bulgaria, September 2015. accepted.


Dokumenttyp:Datenpublikation
Sprache(n):Englisch
DNB-Sachgruppe:004 Informatik
Fakultät:Fakultät für Informatik und Elektrotechnik

Persistente URL:http://purl.uni-rostock.de/rosdok/id00000117
erstellt am:2015-08-14
zuletzt geändert am:2015-08-14
Metadaten-Lizenz:
CC0
Die UB Rostock stellt die Metadaten zu diesem Dokument unter Public Domain und verzichtet damit weltweit auf alle urheberrechtlichen und verwandten Schutzrechte.