I am a Research Scientist for Artificial General Intelligence (AGI) at Amazon in Berlin currently working on Large Language Models (LLMs) for conversational AI. Prior to that, I completed my PhD in the Applied Computational Linguistics Discourse Research Lab (University of Potsdam), under the supervision of Prof. Dr. Manfred Stede.
News
- Our paper on Leveraging Large Language Models for Automated Construction of Scientific Leaderboards has been accepted to EMNLP 2024 main track. Check out the Arxiv version!
- I serve as a Senior Area Chair at EACL 2024, and as an Area Chair at COLING 2025.
- An article about our academic collaboration with the UKP Lab from the Technical Univeristy of Darmstadt has been published in the national press! See here (in German; for English, check out the UKP lab website).
I have been reviewing for NLP conferences ACL, NAACL, EMNLP, COLING, IJCNLP-AACL, LREC, and many co-located workshops, as well as journals Knowledge and Information Systems, Natural Language Engineering, Language Resources and Evaluation.
Publications
2024
- Efficient Performance Tracking: Leveraging Large Language Models for Automated Construction of Scientific Leaderboards.
Furkan Şahinuç, Thy Thy Tran, Yulia Grishina, Yufang Hou, Bei Chen, Iryna Gurevych.
Empirical Methods in Natural Language Processing (EMNLP), Miami, USA. Novermber 2024 (To Appear).
[arXiv]
2023
- Paraphrase Mining Under Divergence Constraints for Improving SLU Model Testing Coverage.
Yulia Grishina, Enrico Piovano, Bei Chen, Melanie Bradford.
ACM 32th International Conference on Information and Knowledge Management (CIKM) 2023 (Applied Research Track), Birmingham, UK. October 2023 (To Appear).
2022
-
Local-to-global learning for iterative training of production SLU models on new features.
Yulia Grishina and Daniil Sorokin.
NAACL 2022 (Industry Track), Seattle, USA. July 2022.
[Amazon Science preprint]
[pdf]
[bibtex]
-
De-biasing training data distribution using targeted data enrichment techniques.
Dieu Thu Le, Jose Garrido Ramas, Yulia Grishina, Kay Rottmann.
4th Workshop on Deep Learning Practice and Theory for High-Dimensional Sparse and Imbalanced Data, @KDD 2022. Washington DC, USA. August 2022.
[Amazon Science preprint]
[pdf]
2020
- Truecasing German noisy conversational text.
Yulia Grishina, Thomas Gueudré, Ralf Winkler.
The 6th Workshop on Noisy User-generated Text (W-NUT) @EMNLP 2020. Virtual. November 2020.
[Amazon Science preprint]
[pdf]
[bibtex]
2019
-
TED Multilingual Discourse Bank (TED-MDB): A parallel corpus annotated in the PDTB style.
Deniz Zeyrek, Amália Mendes, Yulia Grishina, Murathan Kurfali, Samuel Gibbon, Maciej Ogrodniczuk.
Language Resources and Evaluation. April 2019. [pdf] [bibtex]
-
Assessing the applicability of annotation projection methods for coreference relations.
Yulia Grishina.
Ph.D. thesis, University of Potsdam, 2019. [pdf] [bibtex] [urn]
2018
- Anaphora resolution with the ARRAU corpus.
Massimo Poesio, Yulia Grishina, Varada Kolhatkar, Nafise Moosavi, Ina Roesiger, Adam Roussel, Fabian Simonjetz, Alexandra Uma, Olga Uryupina, Juntao Yu, and Heike Zinsmeister.
In Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference @NAACL2018. New Orleans, USA, June 2018. [pdf] [bibtex]
2017
- Combining the output of two coreference resolution systems for two source languages to improve annotation projection.
Yulia Grishina.
In Proceedings of the 3rd Workshop on Discourse in Machine Translation @EMNLP 2017. Copenhagen, Denmark, September 2017. Association for Computational Linguistics. [pdf] [bibtex]
- CORBON 2017 Shared Task: projection-based coreference resolution.
Yulia Grishina.
In Proceedings of the 2nd Coreference Resolution Beyond OntoNotes (CORBON) Workshop @EACL 2017. Valencia, Spain, April 2017. Association for Computational Linguistics. [pdf] [bibtex]
- Toward a bilingual lexical database on connectives: Exploiting a German/Italian parallel corpus.
Peter Bourgonje, Yulia Grishina, and Manfred Stede.
In Proceedings of the Fourth Italian Conference on Computational Linguistics. Rome, Italy, December 2017. [pdf] [bibtex]
- Multi-source projection of coreference chains: Assessing strategies and testing opportunities.
Yulia Grishina and Manfred Stede.
In Proceedings of the 2nd Coreference Resolution Beyond OntoNotes (CORBON) Workshop @EACL 2017. Valencia, Spain, April 2017. Association for Computational Linguistics. [pdf] [bibtex]
2016
- Parallel coreference annotation guidelines.
Yulia Grishina and Manfred Stede.
November 2016. Internal report. [pdf]
- Experiments on bridging across languages and genres.
Yulia Grishina.
In Proceedings of the Coreference Resolution Beyond OntoNotes (CORBON) Workshop @NAACL 2016. San Diego, California, June 2016. Association for Computational Linguistics. [pdf] [bibtex]
- Referring expressions as cohesive devices in multiple languages.
Yulia Grishina and Manfred Stede.
In Proceedings of TextLink–Structuring Discourse in Multilingual Europe Second Action Conference, 55. Karoli Gaspar University of the Reformed Church, Budapest, Hungary, April 2016. [pdf] [bibtex]
- Anaphoricity in connectives: A case study on German.
Manfred Stede and Yulia Grishina.
In Proceedings of the Coreference Resolution Beyond OntoNotes (CORBON) Workshop @NAACL 2016. San Diego, California, June 2016. Association for Computational Linguistics. [pdf] [bibtex]
2015
- Knowledge-lean projection of coreference chains across languages.
Yulia Grishina and Manfred Stede.
In Proceedings of the 8th Workshop on Building and Using Comparable Corpora @ACL 2015. Beijing, China, July 2015. Association for Computational Linguistics. [pdf] [bibtex]
2014
- Conceptual and practical steps in event coreference analysis of large-scale data.
Fatemeh Torabi Asr, Jonathan Sonntag, Yulia Grishina, and Manfred Stede.
In Proceedings of the Second Workshop on EVENTS: Definition, Detection, Coreference, and Representation @ACL 2014, 35–44. Baltimore, Maryland, USA, June 2014. Association for Computational Linguistics. [pdf] [bibtex]