|Iryna Gurevych, Full Professor, Dr.|
Director, Ubiquitous Knowledge Processing (UKP) Lab
Associated with the Leibniz-Institute for Educational Research (DIPF), Frankfurt am Main
|Prof. Dr. Iryna Gurevych|
|+49 (6151) 16 - 25290|
|+49 (6151) 16 - 25295|
|S2|02 B 110|
TU Darmstadt - FB 20
Strong background in lexical-semantics, resources and algorithms, and innovative applications of language processing to social sciences and humanities, including online publishing and educational research. Iryna Gurevych is Founder and Principal Investigator in:
AIPHES: the DFG-funded Research Training Group “Adaptive Information Preparation from Heterogeneous Sources”, Spokesperson
KDSL: the Graduate School “Knowledge Discovery in Scientific Literature”, Director
CEDIFOR: the BMBF-funded Centre for the Digital Foundation of Research in the Humanities, Social, and Educational Sciences, Co-Director
Detailed information about Iryna’s activities can be found through the respective links in the frame to the left of this text.
If you are a young researcher or a student in computer science or Natural Language Processing committed to cutting-edge research and team spirit, consider joining UKP.
Co-Chair, 3rd Workshop on Argument Mining at ACL 2016 in Berlin; co-manager of the workshop's Special Track on Debating Technologies and co-chair of the workshop's Unshared Task on Argument Mining
Co-Chair, "NLP Approaches to Computational Argumentation" tutorial at ACL 2016 in Berlin
Co-Chair, "Argument Mining" course at SSA'16 in Potsdam
Co-Chair, Dagstuhl Seminar “Debating Systems”, Dagstuhl, Germany
2015 - 2016
Scientific Advisory Board Member of EACL.
Fellow at the "Forum für interdisziplinäre Forschung" (Engl.: Board for Interdisciplinary Research) of the Technische Universität Darmstadt.
Member and Chair (since 08.2012) of the Scientific Advisory Board (wissenschaftlicher Beirat) of the German Society for Computational Linguistics and Language Technology (Gesellschaft für Sprachtechnologie & Computerlinguistik, GSCL)
Founder and Chair of the Jury for the GSCL doctoral thesis award in memory of Wolfgang Hoeppner
|Author||Steffen Eger, Erik-Lân Do Dinh, Ilia Kuznetsov, Masoud Kiaeeha, Iryna Gurevych|
|Book title||Proceedings of the International Workshop on Semantic Evaluation|
|Research Areas||UKP_a_DLinNLP, Ubiquitous Knowledge Processing, UKP_reviewed|
|Abstract||This paper describes our approach to the SemEval 2017 Task 10: “Extracting Keyphrases and Relations from Scientific Publications”, specifically to Subtask (B): “Classification of identified keyphrases”. We explored three different deep learning approaches: a character-level convolutional neural network (CNN), a stacked learner with an MLP meta-classifier, and an attention based Bi-LSTM. From these approaches, we created an ensemble of differently hyper-parameterized systems, achieving a micro-F1-score of 0.63 on the test data. Our approach ranks 2nd (score of 1st placed system: 0.64) out of four according to this official score. However, we erroneously trained 2 out of 3 neural nets (the stacker and the CNN) on only roughly 15% of the full data, namely, the original development set. When trained on the full data (training + development), our ensemble has a micro-F1-score of 0.69. Our code is available from https://github.com/UKPLab/semeval2017-scienceie.|