email: Substitute My Last Name Here @cis.uni-muenchen.de
tel.: +49 89 2180-9710
web: http://www.cis.uni-muenchen.de/~fraser

Office: C110
Office hours: by appointment (please email)
Telephone hours: by appointment (please email)

I am a tenured professor with membership in both the Faculty of Languages and Literature (Fak 13) and the Faculty of Mathematics, Computer Science and Statistics (Fak 16, Zweitmitgliedschaft) at LMU Munich. I am interested in the intersection of natural language processing and machine learning.

I am also the coordinator for the Masters in Computational Linguistics at LMU Munich. This is a mostly German language program (however, in addition to German, you must also have a strong competency in English). For more information about applying to the program, please see this link. If you have questions please first contact our Studienberatung.

Recent Activities

• Irina, Alexandra, Tobias and Simon have first author papers at LT-EDI, NAACL, ACL, and MT Summit, see publications, congrats to them and to their coauthors!

• Dr. rer nat: Dario successfully defended his PhD thesis on "Modeling Contextual Information in Neural Machine Translation"! Thank you Prof. Dr. Philipp Koehn and Prof. Dr. Rico Sennrich for being part of the committee.

• We are organizing the WMT 2021 shared task on Unsupervised MT and Very Low Resource Supervised MT. The tasks are to translate Upper Sorbian and Lower Sorbian to/from German, as well as to translate Chuvash to/from Russian. Please participate! More information here.

• Dario presented a key paper for his PhD research showing that document-level context allows domain adaptation to zero-resource domains (domains which did not appear in the training data).

• The SOTRA translator for translation of Upper Sorbian to and from German went live! Here is a link to the press conference (in German with some Upper Sorbian), where I briefly talked about planned future work on the system.

• I was invited to participate in the first meeting of the ELLIS Society Natural Language Processing initiative for two days in February 2021, it was very interesting!

• NEW: all topics are taken, thanks for your applications. [My research group is offering MA and BA topics in SS 2021, please read this page carefully.]

• New papers at EMNLP, COLING and WMT! See publications.

• Viktor is presenting new work on dealing with many-to-one and one-to-many translations (i.e., compositionality) at AMTA 2020. See publications.

• NEW: all topics are taken, thanks for your applications. [My research group is offering MA and BA topics in WS 2020/2021, please read this page carefully]

• I held a talk on recent research at the Faculty of Mathematics, Informatics and Statistics (here at LMU Munich), see here for a video.

• Marion Weller-Di Marco's paper on Modeling Word Formation in English-German Neural Machine Translation appeared at ACL. See publications.

• Silvia Severini and Viktor Hangya (in joint work with Hinrich and myself) had the best results in the Russian-English shared task at BUCC 2020. See publications.

• Congratulations to Leah Michel and Viktor Hangya on a study of the challenges of using standard post-hoc-mapped Bilingual Word Embeddings for the low-resource language Hiligaynon at LREC 2020. See publications.

• We are organizing the WMT 2020 shared task on Unsupervised Machine Translation and Very Low Resource Machine Translation. The tasks are to translate from German to Upper Sorbian, and from Upper Sorbian to German. Please participate! More information here.

• Older activities here

Research

Publications and Research Interests

Curriculum Vitae

ERC Starting Grant (EU Horizon2020)

Health in my Language (HimL) (EU Horizon2020)

Models of Morphosyntax for Statistical Machine Translation (DFG Project (2 phases))

TTC - Terminology Extraction, Translation Tools and Comparable Corpora (EU FP7 Project)

Teaching - Current

Lecture Erweiterungsmodul: Machine Translation (Summer Semester 2021)

Exercise Erweiterungsmodul: Machine Translation (Summer Semester 2021)

Current Topics in NLP (Deep Learning and Neural Machine Translation) (Summer Semester 2021, Fraser, Schütze)

Teaching - Past

click here

Bio

Biography

Post-docs

Dr. Viktor Hangya, ERC

Dr. Jindřich Libovický, ERC, DFG Unsup

Dr. Marion Di Marco (nee Weller), ERC

Dr. Matthias Huck, 04/2016-03/2020, ERC and HimL

Dr. Fabienne Braune, 01/2016-12/2017, ERC and HimL (also Morphosyntax 2)

Dr. Aleš Tamchyna, 01/2017-04/2017. HimL and ERC (jointly supervised with Prof. Jan Hajic, Charles University Prague)

Dr. Tsuyoshi Okita, 01/2016-12/2016, ERC

Dr. Liane Guillou, 04/2016-09/2016, HimL

Ph.D. Students

Wen (Lavine) Lai (with Jindrich Libovicky) 04/2021-, LMU/CSC (visiting from 10/2020-03/2021); Low Resource NMT

Sophie Henning (with Annemarie Friedrich) 01/2021-, Bosch; Calibration

Alexandra Chronopoulou 09/2019-, ERC, DFG Unsup; Multilingual Transfer Learning, Unsupervised MT

Dario Stojanovski 06/2017-06/2021, Modeling Contextual Information in Neural Machine Translation, ERC; Context-Aware NMT, Domain Adaptation, Unsupervised MT

Anita Ramm (nee Gojun), 05/2013-03/2018, Modeling the position and inflection of verbs in English to German machine translation. First position after graduation: BeOne Stuttgart GmbH.

Marion Weller-Di Marco (nee Weller) (with Sabine Schulte im Walde), 12/2011-09/2017, Using Morpho-Syntactic and Semantic Information to Improve Statistical Machine Translation. First position after graduation: Post-doc at University of Amsterdam with Khalil Sima'an.

Fabienne Braune (with Andreas Maletti), 10/2009-11/2015, Decoding Strategies for Syntax-based Statistical Machine Translation. First position after graduation: Post-doc on deep learning and comparable corpora in my group.

Fabienne Cap (nee Fritzinger), 10/2009-10/2014, Morphological Processing of Compounds for Statistical Machine Translation. First position after graduation: Post-doc at Uppsala with Joakim Nivre.

Nadir Durrani (with Helmut Schmid), 04/2008-11/2012, A Joint Translation Model With Integrated Reordering. First position after graduation: Post-doc with Philipp Koehn, U. Edinburgh, Scotland, UK.

Hassan Sajjad (with Helmut Schmid), 04/2008-10/2012, Statistical Models for Unsupervised, Semi-supervised and Supervised Transliteration Mining. First position after graduation: Research Scientist at Qatar Computing Research Institute.

Visiting Ph.D. Students

Prisca Piccirilli (with Sabine Schulte im Walde, U Stuttgart). Topic defined, start date of funding 07/2021

Denis Peskov (University of Maryland College Park). 01/2020 to 10/2020

Simon Rieß (LMU Data Science). 10/2019 to 12/2019

Viktor Hangya (University of Szeged). 10/2016 to 12/2016

Ales Tamchyna (Charles University Prague). 10/2015 to 05/2016

Marija Brkic (University of Zagreb, Croatia). 09/2010 to 02/2011

Information for New Students

Guidelines for students who are interested in visiting

Other Links

USC/ISI Natural Language Group

What I work on (for non-specialists)