ÉVA MÚJDRICZA-MAYDT

Éva Mújdricza-Maydt

Contact

+49 06221 54-3483
Email (click to copy)
Zimmer 122 Institut für Computerlinguistik
Im Neuenheimer Feld 325
D-69120 Heidelberg
Germany
Donnerstag, 11:00–12:00 Uhr, Zimmer 122, INF 325 oder nach Vereinbarung

About me:

I am a PhD student at the Computational Linguistics Group. My supervisor is Prof. Dr. Anette Frank. I am working on Semantic Role Labeling for German.

2013-2016 I was working in the Heidelberg group of F-AG 7 in the CLARIN-D project (Common Language Resources and Technology Infrastructure – Deutschland). The ICL website: CLARIN-D.

I am an associated researcher in AIPHES.

Zuständigkeiten | Responsibilities

TEACHING

SS19

Einführung in wissenschaftliches Schreiben (Block, ÜK)

Mo., 01.04.–Do.,04.04.; 09:00–18:00 s.t., INF 325, CIP-Pool

Semantic Role Labeling (PS)

Mittwoch, 14:15–15:445 Uhr, INF 327 / SR 4

WS18

Designing Experiments for Machine Learning Tasks (PS)

Mittwoch, 16:15–17:45 Uhr, INF 326 / SR 27

Einführung in wissenschaftliches Schreiben (Block, ÜK)

Mo., 08.10.–Do.,11.10.; 09:00–18:00 s.t., INF 325, CIP-Pool

SS18

Einführung in wissenschaftliches Schreiben (Block, ÜK)

Mo., 09.04.–Do.,12.04.; 09:00–18:00 s.t., INF 325, CIP-Pool

WS17

Programmieren 1 (Python) (V)

Dienstag, 16:15 – 17:45 Uhr, INF 306 / HS 1; Donnerstag, 16:15 – 17:45 Uhr, INF 328 / SR 25

SS17

NLP-Werkstatt: Arbeiten mit linguistisch annotierten Korpora (PS+Ü)

Mittwoch, 14:15–15:45 Uhr, INF 329 / SR 26 + Ü INF 325, CIP-Pool

Einführung in wissenschaftliches Schreiben (Block, ÜK)

Di., 18.04.–Fr.,21.04.; 09:00–17:00 s.t., INF 325, CIP-Pool

WS16

Designing Experiments for Machine Learning Tasks (PS)

Mittwoch, 16:15–17:45 Uhr, INF 325 / SR 24

SS16

NLP-Werkstatt: Arbeiten mit linguistisch annotierten Korpora (PS+Ü)

Mittwoch, 14:15–15:45 Uhr, INF 327 / SR 2; Ü INF 325, CIP-Pool

WS15

Designing Experiments for Machine Learning Tasks (PS)

Mittwoch, 16:15–17:45 Uhr, INF 325 / SR 24

SS15

NLP-Werkstatt: Arbeiten mit linguistisch annotierten Korpora (PS)

Mittwoch, 16:15–17:45 Uhr, INF 325 / SR 23

WS14

Designing Experiments for Machine Learning Tasks (PS)

Mittwoch, 16:15–17:45 Uhr, INF 325 / SR 24

SS14

NLP-Werkstatt: Arbeiten mit linguistisch annotierten Korpora (PS)

Mittwoch, 16:15–17:45 Uhr, INF 325 / SR 23

WS13

Designing Experiments for Machine Learning Tasks (PS)

Montag, 14:15–15:45 Uhr, INF 327 / SR 4

Mitbetreuer der Softwareprojekt-Gruppe 2

Elisa Starke, Angelika Kirilin, Mengfei Zhou, Damian Gorski: Learning and predicting verb-argument binding

[ Poster ]

Software

CRFalign

CRFalign: a CRF-based sentence-aligner written in Java, in collaboration with Huiqin Körkel-Qu.

The downloadable compressed folder (3.0 MB) entails

To use the aligner you additionally need the following software:

Publication

Sample data for the aligner

Contact

Mail to me and Huiqin

SR3de Corpus

Semantic Role Triple Dataset for German

Parallel dataset for German SRL with PropBank, VerbNet, and FrameNet annotations of appr. 3000 predicate argument structures out of the CoNLL 2009 shared task German data.

See on http://www.cl.uni-heidelberg.de/projects/SR3de/.

Repository

(Most of the repositories are private. Please, contact me for source code of projects if needed.)

Data

Semantic Annotation

Sample data for the CRFalign aligner:

OpenSubtitles corpus (315 German-English file pairs)

315 German-English movie text pairs from the OpenSubtitle2011 corpus, which was used to train and test the CRF-based sentence aligner CRFalign.

Gutenberg corpus (114 German-English file pairs)

This slightly differing version of the Bilingual Formal / Informal Address Corpus was used to train and test the CRF-based sentence aligner CRFalign.

(* NOTE that one file pair in our training set cannot be provided due to copyright restrictions. See readme.)

PUBLICATIONS

2017
+ -

Assessing SRL Frameworks with Automatic Training Data Expansion

Hartmann, S., Mújdricza-Maydt, É., Kuznetsov, I., Gurevych, I., Frank, A. (2017)

Proceedings of the 11th Linguistic Annotation Workshop (LAW-XI 2017).
2016
+ -

A Web-based Tool for the Integrated Annotation of Semantic and Syntactic Structures

Eckart de Castilho, R., Mújdricza-Maydt, É., Yimam, S., Hartmann, S., Gurevych, I., Frank, A., Biemann, C. (2016)

Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanitites (LT4DH), Osaka, Japan, 76-84

Combining Semantic Annotation of Word Sense & Semantic Roles: A Novel Annotation Scheme for VerbNet Roles on German Language Data

Mújdricza-Maydt, É., Hartmann, S., Gurevych, I., Frank, A. (2016)

Proceedings of the Tenth International Conference on Language Resources and Evaluation, Portorož, Slovenia, 3031-3038
2013
+ -

High Precision Sentence Alignment by Bootstrapping from Wood Standard Annotations

Mújdricza-Maydt, É., Körkel-Qu, H., Riezler, S., Padó, S. (2013)

Prague Bulletin of Mathematical Linguistics, 5-16
2012
+ -

{A multigraph model for coreference resolution}

Martschat, S., Cai, J., Broscheit, S., Mújdricza-Maydt, E., Strube, M. (2012)

Proceedings of the Shared Task of the 16th Conference on Computational Natural Language Learning, Jeju, Korea, 100-106
2011
+ -

{Unrestricted coreference resolution via global hypergraph partitioning}

Cai, J., Mújdricza-Maydt, É., Strube, M. (2011)

Proceedings of the 15th Conference on Computational Natural Language Learning, {\em Portland, Oreg., 23-24 June 2011}, 56-60