T
Tobias Falke
Researcher at Technische Universität Darmstadt
Publications - 19
Citations - 405
Tobias Falke is an academic researcher from Technische Universität Darmstadt. The author has contributed to research in topics: Automatic summarization & Computer science. The author has an hindex of 7, co-authored 16 publications receiving 253 citations. Previous affiliations of Tobias Falke include FernUniversität Hagen.
Papers
More filters
Proceedings ArticleDOI
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference
TL;DR: This paper evaluates summaries produced by state-of-the-art models via crowdsourcing and shows that such errors occur frequently, in particular with more abstractive models, which leads to an interesting downstream application for entailment models.
Proceedings Article
Concept-Map-Based Multi-Document Summarization using Concept Coreference Resolution and Global Importance Optimization
TL;DR: A new model for concept-map-based multi-document summarization is proposed that learns to identify and merge coreferent concepts to reduce redundancy, determines their importance with a strong supervised model and finds an optimal summary concept map via integer linear programming.
Proceedings ArticleDOI
Bringing Structure into Summaries: Crowdsourcing a Benchmark Corpus of Concept Maps
Tobias Falke,Iryna Gurevych +1 more
TL;DR: In this article, a corpus of concept maps that summarize heterogeneous collections of web documents on educational topics was created using a novel crowdsourcing approach that allows us to efficiently determine important elements in large document collections.
Posted Content
Bringing Structure into Summaries: Crowdsourcing a Benchmark Corpus of Concept Maps
Tobias Falke,Iryna Gurevych +1 more
TL;DR: In this paper, a corpus of concept maps that summarize heterogeneous collections of web documents on educational topics was created using a novel crowdsourcing approach that allows us to efficiently determine important elements in large document collections.
Proceedings ArticleDOI
Porting an Open Information Extraction System from English to German
TL;DR: This paper presents a straightforward approach for adapting PropS, a rule-based predicate-argument analysis for English, to a new language, German, and obtains an Open IE system for German covering 89% of the English rule set.