Dr. Fabienne Braune Post-doc Researcher in NLP



Deep learning, multi-lingual word embeddings, text mining, transfer learning, neural machine translation, domain adaptation.

About

I am currently working with Prof. Alexander Fraser on two European research projects. My research focuses on the investigation of deep learning methods for terminology extraction, cross-lingual transfer learning, domain adaptation and neural machine translation. Previously, I worked on syntax-based statistical machine translation and defended a PhD on this topic.


I am giving lectures in the information extraction class and the machine translation seminar. I am also advising students on deep learning approaches for multi-lingual sentence extraction, cross-lingual named-entity recognition and domain adaptation.

Research Interests

  • Deep learning
  • Multi-lingual word embeddings
  • Text mining
  • Cross-lingual transfer learning
  • Neural machine translation
  • Domain adaptation
  • Synchronous grammars



Projects I worked on

Publications

Conferences

Matthias Huck, Fabienne Braune, Alexander Fraser (2017). LMU Munich's Neural Machine Translation Systems for News Articles and Health Information Texts. In Proceedings of the Second ACL Conference on Machine Translation (WMT).

B. Haddow, A. Birch, O. Bojar, F. Braune, C. Davenport, A. Fraser, M. Huck, M. Kašpar, K. Kovařı́ková, J. Plch, A. Ramm, J. Ried, J. Sheary, A. Tamchyna, D. Variš, M. Weller, and P. Williams (2017). HimL: Health in my Language. In Proceedings of the 21th Annual Conference of the European Association for Machine Translation (EAMT).

Fabienne Braune, Alexander Fraser, Hal Daume III and Ales Tamchyna (2016). A Framework for Discriminative Rule Selection in Hierarchical Moses. In Proceedings of the 1st Conference on Machine Translation (WMT).

Nina Seemann, Fabienne Braune, Andreas Maletti (2015). A Systematic Evaluation of MBOT in Statistical Machine Translation. In Proceedings of the 15-th MT Summit (MT Summit).

Fabienne Braune, Nina Seemann, Alexander Fraser (2015). Rule Selection with Soft Syntactic Features for String-to-Tree Statistical Machine Translation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP).

Nina Seemann, Fabienne Braune, Andreas Maletti (2015). String-to-Tree Multi Bottom-up Tree Transducers. In  Proceedings of the 53th Annual Meeting of the Association for Computational Linguistics (ACL).

Fabienne Braune, Daniel Bauer, Kevin Knight (2014). Mapping Between English Strings and Reentrant Semantic Graphs. Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC).

Fabienne Braune, Nina Seemann, Daniel Quernheim, Andreas Maletti (2013). Shallow Local Multi Bottom-up Tree Transducers in Statistical Machine Translation. In  Proceedings of the 51th Annual Meeting of the Association for Computational Linguistics (ACL).

Fabienne Braune, Anita Gojun, Alexander Fraser (2012). Long Distance Reordering During Search for Hierarchical Phrase-based SMT. In Proceedings of the 16th Annual Conference of the European Association for Machine Translation (EAMT).

Aurelie Lagoutte, Fabienne Braune, Daniel Quernheim, Andreas Maletti (2012). Composing Extended Top-down Tree Transducers. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL).

Fabienne Braune, Alexander Fraser (2010). Improved Unsupervised Sentence Alignment for Symmetrical and Asymmetrical Parallel Corpora. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING).

Journals

Ales Tamchyna, Fabienne Braune, Alexander Fraser, Marine Carpuat, Hal Daume III, Chris Quirk (2014) . Integrating a Discriminative Classifier into Phrase-based and Hierarchical Decoding. The Prague Bulletin of Mathematical Linguistics, No. 101, pages 29-41.

Robin Kurtz, Nina Seemann, Fabienne Braune, Andreas Maletti (2013) DIMwid - Decoder Inspection for Moses (using Widgets). The Prague Bulletin of Mathematical Linguistics. No. 100, pages 41-50.

Workshops

Nina Seemann, Daniel Quernheim, Fabienne Braune, and Andreas Maletti (2012). Preservation of Recognizability for Weighted Linear Extended Top-down Tree Transducers. In Frank Drewes and Marco Kuhlmann, editors, Proc. 2nd Workshop Applications of Tree Automata in Natural Language Processing (ATANLP).

Guest Lectures (LMU Munich)

  • Neural Networks and Word Embeddings slides
  • Named-Entity Recognition with Neural Networks slides
  • Bilingual Word Embeddings and Recurrent Neural Networks slides
  • Python and Python Regular Expressions review slides



Supervision (LMU Munich)

Bachelors Theses

  • Jakob Ibrahim Sharab, Predicting New Domain Senses in English Medical Texts , completed 2017
  • Tobias Eder: Exploiting Bilingual Word Embeddings to Establish Translational Equivalence , completed 2017
  • Verena Pongratz, Sense Annotation: Ein semi-automatischer Ansatz für die Korpusübersetzung, completed 2017



Guest Lectures (Uni Stuttgart)

  • Formal Models for NLP
  • Statistical Machine Translation