• Login

Rafael Ehren

SFB 991 / CRC 991

Room: 23.32.02.24
Phone: 0211-81–11708
Email: rafael.ehren@hhu.de

Subject

Linguistics

SToRE Membership

SToRE member since 30.05.2017

1. advisor: Laura Kallmeyer
2. advisor: Wiebke Petersen
3. advisor: Timm Lichte

PhD Project

My dissertation project is concerned with developing a method that automatically disambiguates semantically idiomatic multiword expressions (MWEs) from their literal counterparts. To accomplish this, the first step is to build a corpus of annotated instances of the aforementioned MWEs. This corpus subsequently will be used to train and evaluate a classifier that is capable of differentiating the readings of a target expression by using the information given by its surrounding context. Besides the use of appropriate machine learning algorithms (supervised vs. unsupervised), the main focus of this work will be on finding the features that are best suited for this task.

Publications

Rafael Ehren, Timm Lichte & Younes Samih. 2018. Mumpitz at PARSEME Shared Task 2018: A bidirectional LSTM for the identification of verbal multiword expressions. In Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), 261-267.

Ehren, Rafael. 2017. Literal or idiomatic? Identifying the reading of single occurrences of German multiword expressions using word embeddings. In Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics, 103–112. Valencia, Spain: Association for Computational Linguistics.

Conference presentations

Rafael Ehren, Timm Lichte & Younes Samih. 2018. Mumpitz at PARSEME Shared Task 2018: A bidirectional LSTM for the identification of verbal multiword expressions. Poster at the LAW-MWE-CxG-2018 Workshop, 25.-26. August 2018, Santa Fe.

Fabienne Cap, Rafael Ehren, Maximilian Köper, Timm Lichte, Sabine Schulte im Walde & Heike Zinsmeister. 2018. VerbCompoCor: A German Corpus with Compositionality Judgments for Verb-Dependent Pairs. Poster at the DGfS-CL poster session at the 40th annual DGfS meeting, 07.–09.03.2018, Stuttgart.

Rafael Ehren. 2017. Literal or idiomatic? Identifying the reading of single occurrences of German multiword expressions using word embeddings. Talk at the EACL Student Research Workshop 2017, 3-7 April 2017, Valencia, Spain.

Last updated

11.12.2018