Logo des Repositoriums
 

Is the context-based Word2Vec representation useful to determine Question Words for Generators?

Kurzanzeige
dc.contributor.authorRüdian, Sylvio
dc.contributor.authorPinkwart, Niels
dc.contributor.editorZender, Raphael
dc.contributor.editorIfenthaler, Dirk
dc.contributor.editorLeonhardt, Thiemo
dc.contributor.editorSchumacher, Clara
dc.date.accessioned2020-09-08T09:46:22Z
dc.date.available2020-09-08T09:46:22Z
dc.date.issued2020
dc.description.abstractQuestion and answer generation approaches focus on the quality and correctness of generated questions for online courses but miss to use a good question word, which is a deficiency reported by many previous studies. In this experimental setup, we explored whether the word2vec representation, which is semantic-based, can be used to predict question words. We compare two pipelines of the prediction process and observed that splitting the problem into several subproblems performs similar to feeding a neural network with all the data. Although our approach is promising to take the context-based representation into account we can see that the success rate is still low but better than guessing.en
dc.identifier.isbn978-3-88579-702-9
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/34172
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofDELFI 2020 – Die 18. Fachtagung Bildungstechnologien der Gesellschaft für Informatik e.V.
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-308
dc.subjectQuestion generation
dc.subjectquestion words
dc.subjectonline courses
dc.titleIs the context-based Word2Vec representation useful to determine Question Words for Generators?en
dc.typeText/Conference Paper
gi.citation.endPage294
gi.citation.publisherPlaceBonn
gi.citation.startPage289
gi.conference.date14.-18. September 2020
gi.conference.locationOnline

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
289 DELFI2020_paper_14.pdf
Größe:
181.51 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P308 - DELFI 2020 - Die 18. Fachtagung Bildungstechnologien
DELFI 2020