PhD candidate at the Institute for Logic, Language and Computation of the University of Amsterdam, I work in the Dialogue Modelling Group under the supervision of Raquel Fernández.
I am in love with language interaction and I analyse, model, and try to understand language production and comprehension with computational methods.
My main research goal is proposing and evaluating models of semantic reasoning and pragmatic inference that can be applied to tasks such as dialogue modelling, neural language modelling, and representation learning. I am also interested in psycho- and sociolinguistic studies of variation and change as they provide insights into how to build more resilient and human-compatible language technologies.
It’s-a me, Mario
Born and raised in Italy, I spent three years in Germany as a undergraduate student of Computational Linguistics at the University of Tübingen and then moved to Amsterdam for a Master’s degree in Artificial Intelligence.
During my Bachelor’s studies, I worked both as a teaching and as a research assistant for the Department of General and Computational Linguistics, and I served a five-month internship in the IBM department for social media analytics.
As a Master’s student, I have collected more teaching and research experience, collaborating with an interdisciplinary set of ILLC scholars and students. I graduated with a thesis on the detection and analysis of lexical semantic change.
- [PDF] Mario Giulianelli, Marco Del Tredici, and Raquel Fernández. 2020. Analysing Lexical Semantic Change with Contextualised Word Representations. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL-2020).
- [PDF] Andrey Kutuzov and Mario Giulianelli. 2020. UiO-UvA at SemEval-2020 Task 1: Contextualised Embeddings for Lexical Semantic Change Detection. To appear in the Proceedings of the 14th International Workshop on Semantic Evaluation (SemEval-2020).
- [PDF] Mario Giulianelli, Jack Harding, Florian Mohnert, Dieuwke Hupkes, and Willem Zuidema. 2018. Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information. Best Paper Award at 1st Workshop on Analyzing and Interpreting Neural Networks for NLP (EMNLP-2018).
- [PDF] Mario Giulianelli and Daniel de Kok. 2018. Semi-supervised emotion lexicon expansion with label propagation. Computational Linguistics in the Netherlands Journal 8 (CLIN).
- [PDF] Lexical Semantic Change Analysis with Contextualised Word Representations. Master’s thesis.
- [PDF] Semi-supervised emotion lexicon expansion with label propagation and specialized word embeddings. Bachelor’s thesis.
- Measuring alignment in conversations across topics and linguistic markers.
- Evaluating the syntactic competence of RAN language models.
- Extraction of event graphs from Kafka’s short stories.
Automatic annotation of emotional events and temporal relations.
- Response time of German native speakers reacting to different types of foreign mispronunciations.
- Sentiment analysis, demographic information extraction, behaviour analysis, and users interests extraction
on Italian texts. At IBM Watson Analytics for Social Media.
- Online symposium. 18 May 2020. [PDF] Analysing Lexical Semantic Change with Contextualised Word Representations.
- Poster. 11 October 2019. [PDF] Contextualised Word Representations for Lexical Semantic Change Analysis. EurNLP. London, UK
- Poster. 30 August 2019. Contextualised Word Representations for Lexical Semantic Change Analysis. Interacting Minds. Egmond aan Zee, Netherlands
- Talk. 1 February 2019. Diagnostic Classifiers for Language Models. Cool Logic Seminar - Institute for Logic, Language and Computation, Amsterdam, Netherlands
- Talk. 1 November 2018. Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information, EMNLP 2018, BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, Brussels, Belgium
- Talk. 26 January 2018. [PDF] Semi-supervised emotion lexicon expansion with label propagation, CLIN 2018, Nijmegen, Netherlands
The only way to predict the future is to invent it.