1 code implementation • LREC (MWE) 2022 • Rafael Ehren, Laura Kallmeyer, Timm Lichte
In this paper we examine a BiLSTM architecture for disambiguating verbal potentially idiomatic expressions (PIEs) as to whether they are used in a literal or an idiomatic reading with respect to explainability of its decisions.
no code implementations • WS 2020 • Rafael Ehren, Timm Lichte, Laura Kallmeyer, Jakub Waszczuk
Supervised disambiguation of verbal idioms (VID) poses special demands on the quality and quantity of the annotated data used for learning and evaluation.
1 code implementation • WS 2019 • Jakub Waszczuk, Rafael Ehren, Regina Stodden, Laura Kallmeyer
We propose to tackle the problem of verbal multiword expression (VMWE) identification using a neural graph parsing-based approach.
no code implementations • COLING 2018 • Rafael Ehren, Timm Lichte, Younes Samih
We submitted results for seven languages in the closed track of the task and for one language in the open track.
no code implementations • EACL 2017 • Rafael Ehren
Non-compositional multiword expressions (MWEs) still pose serious issues for a variety of natural language processing tasks and their ubiquity makes it impossible to get around methods which automatically identify these kind of MWEs.