A
Annemarie Friedrich
Researcher at Bosch
Publications - 34
Citations - 627
Annemarie Friedrich is an academic researcher from Bosch. The author has contributed to research in topics: Parsing & Task (project management). The author has an hindex of 10, co-authored 34 publications receiving 490 citations. Previous affiliations of Annemarie Friedrich include Saarland University & Heidelberg University.
Papers
More filters
Book ChapterDOI
Coherent Multi-sentence Video Description with Variable Level of Detail
Anna Rohrbach,Marcus Rohrbach,Marcus Rohrbach,Wei Qiu,Wei Qiu,Annemarie Friedrich,Manfred Pinkal,Bernt Schiele +7 more
TL;DR: This paper follows a two-step approach where it first learns to predict a semantic representation from video and then generates natural language descriptions from it, and model across-sentence consistency at the level of the SR by enforcing a consistent topic.
Book ChapterDOI
Coherent Multi-Sentence Video Description with Variable Level of Detail
Anna Senina,Marcus Rohrbach,Wei Qiu,Annemarie Friedrich,Sikandar Amin,Mykhaylo Andriluka,Manfred Pinkal,Bernt Schiele +7 more
TL;DR: In this article, a two-step approach is used to predict a semantic representation from video and then generate natural language descriptions from the semantic representation, enforcing a consistent topic at the level of the representation.
Proceedings ArticleDOI
Automatic prediction of aspectual class of verbs in context
TL;DR: A semi-supervised approach using linguistically-motivated features and a novel set of distributional features based on representative verb types allows us to predict classes accurately, even for unseen verbs.
Proceedings ArticleDOI
The SOFC-Exp Corpus and Neural Approaches to Information Extraction in the Materials Science Domain
Annemarie Friedrich,Heike Adel,Federico Tomazic,Johannes Hingerl,Renou Benteau,Anika Marusczyk,Lukas Lange +6 more
TL;DR: An annotation scheme for marking information on experiments related to solid oxide fuel cells in scientific publications, such as involved materials and measurement conditions is developed, as well as a SOFC-Exp corpus consisting of 45 open-access scholarly articles annotated by domain experts.
Proceedings ArticleDOI
Situation entity types: automatic classification of clause-level aspect.
TL;DR: It is shown that the sequence labeling approach using distributional information in the form of Brown clusters, as well as syntactic-semantic features targeted to the task, is robust across genres, reaching accuracies of up to 76%.