name: Leon Derczynski
status: Associate Professor of Computer Science
Natural Language Processing + Machine Learning:
online harms · efficient, green NLP · Danish NLP
contact:
email: ld@itu.dk (public, subject to FOI requests)
post: IT University of Copenhagen, Rued Langgaards Vej 7, 2300 Copenhagen, Denmark
Principal Investigator of Strømberg NLP
DANGER: 2020-2024, Aage og Johann Louis-Hansens Fond, 2,5M DKK.
Dementia Analysis for ALS through Eye Information.
Role: Co-I.
ClinRead: 2020-2022, Novo Nordisk Foundation, 544K DKK.
Rapid Clinical Note Mining for New Languages
Role: Sole PI.
LITHME: 2020-2024, EU COST action, €11K.
lithme.eu Language In The Human-Machine Era.
Role: core proposer, management committee.
FaDa: 2020-2021, UFM, 146K DKK.
Enabling language technology for the Faroe Islands and Denmark.
Role: official participant.
Verif-AI: 2020-2022, DFF, 2,9M DKK.
Automatic multilingual misinformation detection and fact verification support.
Role: PI (sole applicant).
Deep Learning Generative Models for Content Structuring: 2019-2022, InnovationsFonden PhD, 1,07M DKK.
Role: PI for ITU.
NLPL: 2017-2020, NordForsk.
www.nlpl.eu.
Nordic Language Processing Laboratory.
Role: PI for ITU.
COMRADES: 2016-2018, EC H2020 IA €2.0M.
www.comrades-project.eu.
Collective platform for community resilience & social innovation during crises.
Role: Co-I for U.Sheffield.
PHEME: 2014-2017, EC FP7 CP €4.3M.
www.pheme.eu.
Computing Veracity - the Fourth Challenge of Big Data. Pheme builds technology for finding how true claims made online are.
Role: co-author, scientific co-ordinator.
uComp: 2013-2016, EC CHIST-ERA €1.25M.
www.ucomp.eu.
Embedded Human Computation for Knowledge Extraction and Evaluation.
Role: named researcher.
TrendMiner: 2011-2014, EC FP7 CP €3.7M. Trendminer on CORDIS. Large-scale, Cross-lingual Trend Mining and Summarisation of Real-time Media Streams.
personal: github.com/leondz
ITU NLP: github.com/ITUnlp
GATE: github.com/GateNLP
Sheffield NLP: github.com/sheffieldnlp
Leon Derczynski
also: Leon Strømberg-Derczynski
View CV
Google Scholar: user=d8iwqa8AAAAJ
ORCID: 0000-0002-8656-3431
DBLP: Derczynski:Leon
3918 citations
26 h-index
52 i10-index
2021 04 26 at date
2018.08.2x: Program co-chair at COLING 2018, Santa Fe
2018.11.01: Dimensions of Variation in User-generated Text at the Workshop on Noisy User-generated Text (W-NUT), Brussels
2018.11.08: Fake News and Troll Detection at SLTC, Stockholm
2019.Q1: Guest lecturing ML & NLP at Innopolis University, Kazan, Russian Federation
2019.05.06: Opening keynote at Nordic Disinformation conference
2019.05.23: Automatic Detection of Fake News at PET, the Danish Security and Intelligence Service
2019.11.28: Sociolinguistics from data on the back of an envelope, at DIGHUMLAB's AI workshop Aarhus University
2020.05.22: Plenary talk at workshop on Trolling, Aggression and Cyberbullying
2020
Nat Sci Rep: . 2020. Mental Health-Related Conversations on Social Media and Crisis Episodes: A Time-Series Regression Analysis
to appear: . 2020. Directions in Abusive Language Training Data
2019
TTO: . 2019. Misinformation on Twitter During the Danish National Election: A Case Study
NAACL: . 2019. Quantifying the morphosyntactic content of Brown Clusters
2018
COLING: . 2018. Proceedings of the 27th International Conference on Computational Linguistics
ISCRAM: . 2018. Helping Crisis Responders Find the Informative Needle in the Tweet Haystack
2017
book: . 2017. Automatically ordering events and times in text
CSL: . 2017. Generalisation in Named Entity Recognition: A Quantitative Analysis
2016
COLING: . 2016. Broad Twitter Corpus: A Diverse Named Entity Recognition Resource
AAAI: . 2016. Generalised Brown Clustering and Roll-up Feature Generation
2015
IPM: . 2015. Analysis of Named Entity Recognition and Linking for Tweets
SemEval: . 2015. SemEval-2015 Task 6: Clinical TempEval
WEBIST: . 2015. Enhanced Information Access to Social Streams through Word Clouds with Entity Grouping - best paper
2014
EACL: . 2014. Passive-Aggressive Sequence Labeling with Discriminative Post-Editing for Recognising Person Entities in Tweets
EACL: . 2014. DKIE: Open Source Information Extraction for Danish
EACL: . 2014. The GATE Crowdsourcing Plugin: Crowdsourcing Annotated Corpora Made Easy
2013
ACL: . 2013. Temporal Signals Help Label Temporal Relations
SemEval: . 2013. SemEval-2013 Task 1: TempEval-3: Evaluating Events, Time Expressions, and Temporal Relations.
ACM HyperText: . 2013. Microblog-Genre Noise and Impact on Semantic Annotation Accuracy
EDBT: . 2013. Towards Context-Aware Search and Analysis on Social Media Data
2012
LREC: . 2012. TIMEN: An Open Temporal Expression Normalization Resource
Relative position of Starman (live data)
EARTH:km :mi VEL:km/s :km/h :mph (origin)
I'm always open to supervising motivated and capable students, for thesis or other project work.
Open projects are described on a dedicated page:
View open research projects.
_ █
2020.02 We received global press coverage for our work on mental health analysis through twitter
2019.11 Our work on Bornholmsk language technology received national press coverage (Danish): »Ijn bruner katt«: Kunstig intelligens skal redde truet dansk dialekt
2019.05 I wrote a series of data-driven articles on the Danish national election for the press (Danish): Mandag Morgen
2018.10 Dagbladenes Bureau interviewed me on using AI to hire people (Danish): Ansat af en maskine
2018.08 I was program co-chair for COLING 2018 (we had 1018 full paper submissions)
2018.07 Read an interview with me in "Alt om Data" (Danish): Nye sandheder om falske nyheder
brown (generalised)
\[ MI(C_i,C_j)= p(\left< C_i,C_j\right>)\ \log_2{\frac{p(\left<\ C_i,C_j\right>)}{p(\left< C_i,*\right>)\ p(\left<*,C_j\right>)}} \]
\[ AMI(C) = \sum_{C_i,C_j\in C}{MI(C_i,C_j)} \]
\[ C_{i\leftarrow j} = \left( C \setminus \left\{C_i,C_j\right\} \right) \cup \left\{C_i \cup C_j \right\} \]
\[ 0 < a \leq ||C|| \]
\[ i,j \in [1..a] \]
\[ \DeclareMathOperator*{\argmax}{arg\,max} \hat{\pi}(C) = \argmax_{C_i,C_j\in C,i\neq j}{\ AMI(C) - AMI(C_{i\leftarrow j})}. \]
My team at ITU is Strømberg NLP.
I co-ordinate "NLP South" at the IT University of Copenhagen, and am also affiliated within the Machine Learning group and the Natural Language Processing group.
Available RA, PhD, postdoc and faculty positions are announced via the ITU job board, where you can also create alerts for new positions.
Natural Language Processing / Text Mining
Misinformation & stance - how do we determine truth of claims on the web? What behaviours exist around false news? How do we know that the data your system is processing is geniune and accurate?
Processing sparse + noisy data - including social media data, clinical text, and minority languages
Clinical text mining - and pre-clinical public health. Continuing previous associations with Mayo Clinic, NHS SLaM, and Harvard Children's hospital
Danish NLP - Improve the environment that you live in
keywords: natural language processing, machine learning, veracity, clinical nlp social media, artificial intelligence, dansk