Zuständigkeiten | Responsibilities
- Fachstudienberatung:
studienberatung-bachelor
cl.uni-heidelberg.de
- Fachrat (Mitglied seit Mai 2014 bis Ende SoSe19)
- Orientierungstest für Studieninteressierte (Ansprechpartnerin für das Fach Computerlinguistik): http://www.was-studiere-ich.de
- Schnupperstudium
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
- the source code
- readme
- setup
- required external resources (except software listed below)
To use the aligner you additionally need the following software:
Publication
- Éva Mújdricza-Maydt, Huiqin Körkel-Qu, Stefan Riezler, Sebastian Padó (2013): High-Precision Sentence Alignment
by Bootstrapping from Wood Standard Annotations. The Prague Bulletin of Mathematical Linguistics No. 99,
pp. 5-16. [pdf]
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
- SemAnno Corpus: combined verb sense and
semantic role annotation:
for appr. 3500 annotated verbal predicates, the predicates are annotated with GermaNet 9.0 senses, and their
arguments are annotated for each of the predicate senses with VerbNet-style semantic roles.
- SR3de Corpus: 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.
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
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).
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.
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.
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.
{A multigraph model for coreference resolution}
Martschat, S., Cai, J., Broscheit, S., Mújdricza-Maydt, É., Strube, M. (2012)
Proceedings of the Shared Task of the 16th Conference on Computational Natural Language Learning, Jeju, Korea.
{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}.
