At last, a computer that understands you like your mother.
--1985, McDonnell-Douglas ad (Lee, 2004)
Announcements
Selected Keynotes, talks, panel participations
- June (postponed from January) 2022: Keynote speaker at CliC-It 2021, Milan
- June 2022: Keynote speaker at SAIS 2022, Stockholm
- May 2022: Keynote speaker at ACL Workshop on Insights from Negative Results in NLP, Dublin
- December 2021: Invited speaker at the NeurIPS workshop on Efficient Natural Language and Speech Processing and keynote speaker at ALTA 2021 (Australasian Language Technology Association)
- October 2021: Invited speaker and panel discussion at the Workshop on Ethics, AI, Technology and Society organized by Chalmers University at the Världskulturmuseet in Göteborg, Sweden
- September 2021: Invited speaker at the DALI end-of-project workshop at Queen Mary University, London
- August 2021: Career panel discussion at ESSLLI 2021 (with Marco Baroni and Noah Smith)
- July 2021: Invited talk at the 2nd ELLIS NLP workshop
- July 2021: Invited talk on Transfer and Multi-Task Learning in NLP at LxMLS (Lisbon machine learning summer school) 2021. You can find the video lectures on YouTube
- May 2021: Panel discussion at WAIN, ICSE (Software Engineering and AI)
- May 2021: Invited talks at Cambridge University and Uppsala University
- December 2020: Keynote on Tackling the long tail in NLP: Transfer to low-resource language, varieties and dialects at Vardial (COLING 2020)
- November 2020: Panel discussion at WASP4ALL (Virtual Worlds for Artificial Intelligence)
- September 2019: Opening keynote on Deep Transfer Learning: Learning across Languages, Modalities and Tasks at the NLPL workshop on Deep Learning and Natural Language Processing, Turku
- August 2019: I gave a keynote on Transfering NLP models across domains and languages at SyntaxFest, Paris
- May 2019: I gave an invited talk on Deep Learning for Natural Language Processing at IDA AI Event, Copenhagen
- December 2018: I gave an invited talk on Multi-task Learning in Natural Language Processing at Turku AI Meetup, Finland, December 19, 2018
- December 2018: I gave an invited talk on Transfer Learning in Turku, Finland, December 19, 2018
- November 2018: I gave a keynote on "Learning X^2: Natural Language Processing across Languages and Domains" at the UDW 2018 workshop at EMNLP 2018
- June 2018: I gave an invited talk at the LCT day 2018 in Nancy, France, June 27, 2018
- 2017-2018: NAACL 2018 area chair
- June 2018: Invited talk at Uppsala University, Lectures on Language Technology and Machine Learning, Uppsala, June 8, 2018
- June 2018: WiNLP 2018 career panel discussion, New Orleans, June 2, 2018
- June 2018: NAACL 2018 ethics in NLP panel discussion, New Orleans, June 3, 2018
- June 2018: keynote speaker at the NAACL workshop on Stylistic Variation, New Orleans, June 5, 2018
- June 2018: keynote speaker at the NAACL workshop on Subword & Character Level Models in NLP (SCLeM), New Orleans, June 6, 2018
- March 2018: visiting scholar at University of Malta
- March 2018: talk at the Natural Language Processing MeetUp at the University of Zurich, March 20, 2018
- March 2018 talk at Women in Data Science WiDS 2018, Zurich, March 21, 2018
- November 2017: Visited Edinburgh NLP to give a talk at the ILLC colloqium series (November 24, 2017)
- September 2017: I won the IJCNLP 2017 shared task on multilingual customer feedback analysis (ranked 1st / 12 teams)!
- September 6-11: I'll be at EMNLP 2017, Copenhagen
- July 28-29: Excited to be invited speaker at the Google NLU (Natural Language Understanding) workshop, New York
- July 2017: keynote speaker at PyData, Berlin, July, 2017
- 2016-2017: ACL 2017 area co-chair (for tagging, chunking and parsing)
- 2016-2017: EACL 2017 student research workshop senior faculty advisor
Community service (selected)
- 2019-2022: Advisory board officer for EACL, the European Chapter of the Association for Computational Linguistics
- 2019-2022: Elected ACL publicity director. I'm excited to help shape this new ACL executive++ role
- 2021: Co-organizer of Adapt-NLP 2021 (EACL workshop)
- 2021: Co-organizer of WeaSul 2021 (Weak Supervision, ICLR workshop)
- 2018-2019: Program co-chair of the first edition of the European NLP Summit - EurNLP (pronounce "your NLP"), Facebook, London, October, 11, 2019
- 2018-2019: General chair of NoDaLiDa 2019 (the 22nd Nordic Conference on Computational Linguistics) 2019, to be held in Turku September 30-October 2, 2019
- 2018-2019: Co-Chair of the first Women in Data Science conference (WiDS) in Copenhagen on April 16, 2019 together with Natalie Schluter
- 2018-2019: ACL 2019 workshop chair together with Sebastian Riedel
- 2017-2018: ESSLLI 2018 program co-chair for language and computation , with Noah Goodman (Stanford University, USA)
- 2017-2019: Editorial board member of the Computational Linguistics journal
- 2018-2020: Editoral team of the Transactions of the Association for Computational Linguistics (TACL) journal
MaiNLP Research Lab @CIS LMU
We are the MaiNLP research lab @CIS, the Center for Information and Language Processing at LMU Munich. We carry out research in Natural Language Processing, an interdisciplinary subdiscipline of Artificial Intelligence at the interface of computer science, linguistics and cognitive science. In broad terms, our aim is to make NLP models more robust, so that they can deal better with underlying shifts in data due to language variation. This can be among many dimensions, such as language shifts, domain or genre shifts, etc.
Research interests:- learning under sample selection bias (domain adaptation, transfer learning) and annotation bias
- learning under limited data, continual learning, semi-supervised and weakly-supervised machine learning applied to cross-domain and cross-language natural language processing.
- multimodal learning, including learning at the language and vision or speech interface and learning from human data
- fortuitous supervision to enable variety-space aware natural language understanding
- ERC Consolidator grant
- Munich Center for Machine Learning (MCML)
- Danmarks Frie Forskningsfond (DFF) Sapere Aude Research Leader Project MultiVaLUe: Multilingual Variety-Aware Natural Language Understanding
- Danmarks Frie Forskningsfond (DFF) Project 1 MultiSkill: Multilingual Information Extraction for Job Market Analysis
- Kristian Nørgaard Jensen (IT University of Copenhagen) (2020-2022), research assistant
- Sif Dam Sonniks (IT University of Copenhagen) (2020-2022), research support staff
- Rob van de Goot, postdoc, Amazon Research Award co-funded, 2019-2021
- Alan Ramponi (visiting PhD fellow 2019-2020, Trento University and COSBI): biomedical NLP, domain adaptation - now postdoc at FBK, Italy
- Sigrid Klerke (2018-2019), postdoc: human data (eye tracking) to inform NLP - now Chief Data Analyst at EyeJustRead
- Hiêu Lâm (2022), co-supervised with Christian Hardmeier
- Cathrine Damgaard (2021)
- Paulina Kamila Toborek (2021)
- Trine Naja Eriksen (2021)
- Benjamin Olsen (2021)
- Nicolaj Filrup Rasmussen (2020)
- Kristian Nørgaard Jensen (2020, 2021, 2022)
- Marco Placenti (2020)
- Thai Wang (2020)
- Anders Friis Kaas (2020)
- Viktor Torp Thomsen (2020)
- Anders Giovanni Møller (2020)
- Frederik Gaasdal Jensen (2020)
- Alan Ramponi (external PhD, 2019-2020); now postdoc at Univeristy of Trento
- Hessel Haagsma (PhD, co-supervised with Johan Bos, 2017)
- Johannes Bjerva (PhD, co-supervised with Johan Bos, 2017) (defended December 2017); now tenure-track Assistant Professor at Aalborg University, campus Copenhagen
- Reinard van Dalen (Groningen), now at the University of Groningen and self-employed
- Jovana Urosevic (Malta, co-supervised with Lonneke van der Plas), now at LinkedIn
- Masha Medvedeva (Groningen), now PhD student at the University of Groningen
- Jorrit Bakker (Groningen), now at ANIOS intensive care (hospital)
- Esther van den Berg (EM LCT, joint supervision with Dietrich Klakow), now PhD student at University of Heidelberg
- Carsten Lygteskov Hansen (IT & Cognition, University of Copenhagen), now at TextKernel
- Kiona Krueger Weisel (IT & Cognition, University of Copenhagen), now PhD student at University of Erlangen Nuremberg
- Peter Halkier Nicolajsen (IT & Cognition, University of Copenhagen), now at LEGO
- Barbara Plank. What to do about non-standard (or non-canonical) language in NLP. In KONVENS 2016. [arXiv]
- Barbara Plank. Keystroke dynamics as signal for shallow syntactic parsing. The 26 th International Conference on Computational Linguistics (COLING). Osaka, Japan. [arXiv]
- Barbara Plank et al., 2016. Improving language technology with fortuitous data, ESSLLI 2016 summer school.
Lab Members
We are part of the CIS at LMU. You can find us at Akademiestr. 7, 80799 Munich.
Lab members at ITU are part of the Computer Science department at ITU and affiliated with the NLP north research unit at Rued Langaards Vej 7, 2300 Copenhagen S.
Projects and Funding
On-going
Former Lab Members & Alumni
Postdoctoral researchers, PhDs, research assistants and support staff
ITU Bachelor and Master students
Earlier Supervision (selection)
PhD students
Master students
Fortuitous data
Ultimately, NLP should be able to handle any language and any domain. However, there is still a long way to go! Our models need training data,
but annotated data is biased and scarce.
One way to address this problem of training data sparsity is to leverage data that so far has been neglected or rests in non-obvious places. Such fortuitous data [1] includes using hyperlinks to build more robust Part-of-Speech taggers or named-entity recognizers, learning from annotator disagreement and using behavioral data such as gaze or keystrokes [2] to inform NLP. Read up more:
- References:
