Download poster AMLAP 2023: Adaptive Resonance Theory as a computational model of learning inflection classes
- Dekker, P., Klamer, M & de Boer, B. (2022). Universal and language-specific factors behind morphological simplification: An agent-based modelling study of Alorese. In Proceedings of the Joint Conference on Language Evolution 2022. Kanazawa, Japan. [pdf]
- Dekker, P., & Zuidema, W. (2021). Word prediction in computational historical linguistics. Journal of Language Modelling, 8(2), 295–336. https://doi.org/10.15398/jlm.v8i2.268 [pdf] [code]
- Creten, S., Dekker, P., & Vandeghinste, V. (2020). Linguistic Enrichment of Historical Dutch using Deep Learning. Computational Linguistics in the Netherlands Journal, 10, 57-72. [pdf]
- Dekker, P. & Schoonheim, T. (2018). Crowdsourcing Language Resources for Dutch using PYBOSSA: Case Studies on Blends, Neologisms and Language Variation. In Proceedings of the enetCollect WG3&WG5 Meeting, 24-25 October 2018, Leiden, Netherlands. [pdf]
- Dekker, P. (2018). Reconstructing language ancestry by performing word prediction with neural networks (Master’s thesis). [pdf]
- Balog, K., Schuth, A., Dekker, P., Tavakolpoursaleh, N., Schaer, P., Chuang, P-Y., Wu, J., & Giles, C.L. (2016). Overview of the TREC 2016 Open Search track: Academic Search Edition. In E.M. Voorhees & A. Ellis (Eds.) Proceedings of the Twenty-Fifth Text REtrieval Conference (TREC 2016). NIST. [pdf]
- Dekker, P. (2014). Determining Dutch dialect phylogeny using bayesian inference (Bachelor’s thesis). Utrecht University. [pdf]
- Dekker, P., Rasilo, H. & de Boer, B. (2023). Adaptive Resonance Theory as a computational model of learning inflection classes. Architectures and Mechanisms for Language Processing (AMLAP). 31 August – 2 September 2023, Donostia-San Sebastian, Spain. [poster]
- Dekker, P., Gipper, S., Klamer, M., de Boer, B. (2023). Agent-based simulations of affix change: Interacting mechanisms under social dynamics. Affixes Symposium. 17-18 August 2023, Turku, Finland. [presentation] [abstract]
- Introductory presentation at thematic panel “Agent-based modelling in historical sociolinguistics” at the Historical Sociolinguistics Network Conference (HiSoN), 31 May – 2 June 2023, Brussels.
- Dekker, P. (2022). Explaining the processes of change behind a phylogenetic tree: Agent-based models and coalescent simulations. Presentation in Comparative Bioacoustics group, MPI for Psycholinguistics, Nijmegen, 7 February 2022.
- Dekker, P. & de Boer, B. (2022). Learning inflection classes using Adaptive Resonance Theory. Poster in Workshop “Machine learning and the evolution of language”, Joint Conference of Language Evolution, 5-8 September 2022, Kanazawa, Japan.
- Dekker, P. (2022). Agent-based models to evaluate mechanisms behind language change. Conversational priming and other case studies. Invited talk at Historical linguistics colloquium, Universität zu Köln. 1 July 2022.
- Dekker, P. (2022). Verspreidt innovatie door herhaling? Cognitieve en sociale factoren in agent-gebaseerde modellen van conversational priming. Invited talk for variation linguists at Meertens Instituut, Amsterdam. 13 June 2022.
- Dekker, P., Gipper, S. & de Boer, B. (2022). Cognitive and social factors in agent-based models of conversational priming in repetitional responses. Workshop “Cognitive and Cultural Influences on Language Emergence” (CCILE 2022), virtual. 25-27 May 2022. [recording] [slides]
- Dekker, P. & Gipper, S. (2021). Do repetitional responses boost the transmission of linguistic innovations? Evidence from agent-based modelling. Workshop “Conversational Priming in Language Change”, Universität zu Köln. 3-4 December 2021.
- Dekker, P., Klamer, M. & de Boer, B. (2021). Analysing contact–induced simplification in Alorese using agent–based models. 54th Annual Meeting of the Societas Linguistica Europaea, 30 August – 3 September 2021.
- Presentation Katie Mudd & Peter Dekker (2021): Workshop “Language preservation and agent-based computer simulations”. [pdf]
- Dekker, P. & de Boer, B. (2020). Neural Agent-based Models To Study Language Contact Using Linguistic Data. 4th NeurIPS Workshop on Emergent Communication. [poster & abstract]
- Creten, S., Dekker, P. & Vandeghinste, V. (2020). Linguistic enrichment of historical Dutch using deep learning. Computational Linguistics in the Netherlands 30, Utrecht, 2020. [abstract]
- Dekker, P., Fannee, M. & de Does, J. (2019). CLARIAH Chaining Search: A Platform for Combined Exploitation of Multiple Linguistic Resources. CLARIN Annual Conference, Leipzig, 2019. [pdf]
- Dekker, P., Zingano Kuhn, T., Šandrih, B., Zviel-Girshin, R., Arhar Holdt, Š. and Schoonheim, T. (2019). Corpus Cleaning via Crowdsourcing for Developing a Learner’s Dictionary. eLex 2019: Smart Lexicography, 2019.
- Zingano Kuhn, T., Dekker, P., Šandrih, B., Zviel-Girshin, R., Arhar Holdt, Š. and Schoonheim, T. (2019). Crowdsourcing Corpus Cleaning for Language Learning Resource Development. EuroCALL 2019.
- Zingano Kuhn, T., Dekker, P., Šandrih, B., Zviel-Girshin, R. (2019). Crowdsourcing corpus cleaning for language learning – an approach proposal. enetCollect 3th annual meeting. Lisbon. 14-15 March 2019 [pdf]
- Dekker, P. & Schoonheim, T. (2018). When to use PYBOSSA? Case studies on crowdsourcing for Dutch. enetCollect WG1 workshop Gothenburg. 5-7 December 2018. [pdf]
- Dekker, P. & Schoonheim, T. (2018). Recognizing blends: First experiments with PYBOSSA. enetCollect WG3&WG5 meeting Leiden. 24-25 October 2018. [pdf]
- Dekker, P. (2017). Reconstructing language ancestry by performing word prediction. Workshop Phylogenetic Methods in Historical Linguistics. Tübingen. 29-03-17. [pdf]
- Computersimulaties laten zien hoe taal versimpelt, blog in online science magazine Eos Wetenschap and Wtnschp.be, 09-06-2021.
- Gaat een steenoud sterrenbeeldverhaal helemaal terug naar de prehistorie?, contribution to Dutch newspaper article, Ronald Veldhuizen, De Volkskrant, 27-02-2021. [pdf]
- Neural networks help discover how languages are related, blog on MSc thesis, ILLC CLC Lab website, 19-11-2019.
- Ga lekker zitten, Dutch blog on usage of lekker using crowdsourcing research, with Laura van Eerten, Neerlandistiek.nl, 28-02-2019.
Demo: Languages competing in a city. The demo shows how agent-based simulations can help give better insight in real-world situations.
- Stefano Claes (2022, VUB). Statistical and computational analyses of phonotactic data from languages.
- Flynn Steppe (2022, VUB). The development of a system of speech sounds. [code]
- Joni Muyshondt (2022, VUB). Using Restricted Boltzmann Machines in an agent-based model to study language change. [code]
- Lucas Conchuela Nogales (2021, VUB). Using coalescent simulations to test hypotheses of language change.
- Cassandra Moyson (2021, VUB). Using agent-based modeling to investigate the effect of social structure on sign language structure. (co-supervised with Katie Mudd)
- Silke Creten (2019, KU Leuven). Linguistic enrichment of historical Dutch using deep learning. (co-supervised with Vincent Vandeghinste)
Teaching assistant Evolution of language and music (2017-2018), BSc Psychobiology, UvA