// joachim bingel

I'm a Postdoc at the CoAStaL NLP group, University of Copenhagen, working with Anders Søgaard.

My research focuses on automatic text simplification. In particular, I investigate how texts can be adapted to match the needs of specific readers. Other research interests include dialog systems, machine learning (in particular, multitask learning), using cognitive data to improve NLP systems, and corpus linguistics.

I also did my PhD at CoAStaL, advised by Anders. Before coming to Copenhagen, I spent great years at the Institute for Computational Linguistics in Heidelberg, at Uppsala University, and at the Institute for the German Language (IDS Mannheim).

For more info, see my CV.

Joachim Bingel

// contact

// media

Some articles have been published about my work on a web browser plugin that simplifies texts according to individual user profiles. Here's a few of them:

[en] UCPH researcher behind new application for dyslexics
[da] Nyt plugin: Kunstig intelligens hjælper ordblinde med at læse på nettet (Version 2)
[da] Gratis AI-software kan hjælpe ordblinde med at læse (Rbot.dk)

Nota also published two articles about my PhD project as a whole (in Danish).

Tekstprogram skal gøre læsning nemmere
Med læsningen som adgang til samfundet

There's also a video about Lexi that has been published by Nota. Watch it on YouTube.

// publications

2019

González, A.; Petrén Bach Hansen, V.; Bingel, J.; Søgaard, A (2019): CoAStaL at SemEval-2019 Task 3: Affect Classification in Dialogue using Attentive BiLSTMs. In SemEval. Minneapolis, USA.

Ruder, S.; Bingel, J.; Augenstein, I.; Søgaard, A. (2019). Latent Multi-task Architecture Learning. AAAI 2019, Honolulu, Hawaii [ pdf | code ]

2018

Bingel, J. (2018): Personalized and adaptive text simplificaiton.. Ph.D. thesis. University of Copenhagen. [ pdf ]

Barrett, M.; Bingel, J.; Hollenstein, N.; Rei, M. and Søgaard, A. (2018): Sequence classification with human attention. In CoNLL. Brussels, Belgium. [Special Paper Award]

Bollmann, M.; Søgaard, A. and Bingel, J. (2018): Multi-task learning for historical text normalization: Size matters.. In Workshop on Deep Learning Approaches for Low-Resource NLP 2018.. Melbourne, Australia.

Bingel, J.; Paetzold, G. H. and Søgaard, A. (2018): Lexi: a tool for adaptive, personalized text simplification. In COLING. Santa Fe, USA.

Bingel, J. and Bjerva, J. (2018): Cross-lingual complex word identification with Multitask Learning. In CWI 2018 Shared Task at the 13th Workshop on Innovative Use of NLP for Building Educational Applications (BEA). New Orleans, USA.

Bingel, J.; Barrett, M. and Klerke, S. (2018): Predicting Misreadings from Gaze in Children with Reading Difficulties. In 13th Workshop on Innovative Use of NLP for Building Educational Applications (BEA). New Orleans, USA.

Waseem Butt, Z., Thorne, J. and Bingel, J. (2018): Bridging the Gaps: Multi-Task Learning for Domain Transfer of Hate Speech Detection.. In Goldbeck, Jennifer (ed.): Online Harassment. Springer, London.

2017

Alva Manchego, F.; Bingel, J.; Scarton, C.; Paetzold, G. H.; Specia, L. (2017): Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs. In IJCNLP 2017, Taipei.

Ruder, S.; Bingel, J.; Augenstein, I.; Søgaard, A. (2017): Sluice networks: Learning what to share between loosely related tasks. [arXiv]

Bollmann, M.; Bingel, J.; Søgaard, A. (2017): Learning attention for historical text normalization by learning to pronounce. In ACL 2017. Vancouver, Canada.

Bingel, J.; Søgaard, A. (2017): Identifying beneficial task relations for multi-task learning in deep neural networks. In EACL 2017. Valencia, Spain.

2016

Bingel, J.; Barrett, M.; Søgaard, A. (2016): Extracting token-level signals of syntactic processing from fMRI - with an application to PoS induction. In ACL 2016. Berlin, Germany.

Bingel, J.; Søgaard, A. (2016): Text simplification as tree labeling. In ACL 2016. Berlin, Germany.

Barrett, M.; Bingel, J.; Keller, F., Søgaard, A. (2016): Weakly supervised part-of-speech tagging using eye-tracking data. In ACL 2016. Berlin, Germany.

Diewald, N.; Hanl, M.; Margaretha, E.; Bingel, J.; Kupietz, M.; Banski, P. and Witt, A. (2016): KorAP Architecture – Diving in the Deep Sea of Corpus Data. In LREC 2016. Portoroz, Slovenia

Bingel, J.; Schluter, N; and Martínez Alonso, H. (2016): The importance of designing your Neural Networks right. In SemEval 2016 Shared Task 11: Complex Word Identification. San Diego, California.

— 2015

Bingel, J. and Diewald, N. (2015): KoralQuery — A General Corpus Query Protocol. In: Innovative Corpus Query and Visualization Tools at NODALIDA 2015. Vilnius, Lithuania.

Bingel, J. and Haider, T. (2014): Named-Entity Tagging a Very Large Unbalanced Corpus. Training and Evaluating NE classifiers. In: LREC 2014. Reykjavik, Iceland. [ pdf | html ]

Fiedler, N.; Werthmann, A.; Stührenberg, M.; Schonefeld, O.; Bingel, J. and Witt, A. (2014): Forschungsinfrastrukturen an außeruniversitären Forschungseinrichtungen. Research Report. [ pdf | html ]

Bański, P.; Bingel, J.; Diewald, N.; Frick, E.; Hanl, M.; Kupietz, M.; Pęzik, P.; Schnober, C. and A. Witt. (2013): KorAP: the new corpus analysis platform at IDS Mannheim. In: Human Language Technologies as a Challenge for Computer Science and Linguistics. Proceedings of the 6th Language and Technology Conference. Poznań: Fundacja Uniwersytetu im. A. Mickiewicza. ISBN 978-83-932640-3-2 [ pdf ]

// miscellaneous

Time for some linguistic nerdity. I pronounce my first name [ˌjoˈaxɪm] (note the main stress is on the second syllable, which consists only of /a/). For non-German speakers though, I understand this will be difficult, and I tend to introduce myself (and accept varieties) depending on the sociolinguistic situation around me, e.g. English ([ˈdʒəʊ.əkɪm]), Danish ([ˈjoækimˀ]), Swedish ([ˈjuːakɪm])... The last name is ['bɪŋl̩] (the 'ng' as in strong).