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 analyse and model language production and comprehension with computational methods. My main research goal is defining empirical measures of human-likeness that can be used (i) to evaluate the alignment of machine-generated utterances to human communication patterns and strategies, and (ii) to develop NLG models that more closely follow such patterns and strategies. I am also interested in psycholinguistic 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.

News

• New interpretability paper with Sam Ryb at *SEM 2022!
• New paper at the LChange’22 ACL Workshop with Andrey Kutuzov and Lidia Pivovarova. See you in Dublin!
• Invited talk on 14 March at the Language Technology Group Seminar of the Univerisity of Oslo.
• New paper at EMNLP-2021 with Arabella Sinclair and Raquel Fernández.
• Two new papers at CONLL-2021 with Raquel Fernández, Andrey Kutuzov and Lidia Pivovarova.
• Three tasks (with new datasets) accepted for the BIG-bench collaborative benchmark, thanks to an amazing team of students and researchers brought together by the Amsterdam ELLIS unit.
• Excited to co-organise the fourth edition of the BlackboxNLP workshop, which will take place on November 11th at EMNLP.

My work

• Mario Giulianelli, Andrey Kutuzov, Lidia Pivovarova. 2022. Do Not Fire the Linguist: Grammatical Profiles Help Language Models Detect Semantic Change. To appear in Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change.
• Samuel Ryb, Mario Giulianelli, Arabella Sinclair, Raquel Fernández. 2022. AnaLog: Testing Analytical and Deductive Logic Learnability in Language Models. To appear in Proceedings of *SEM 2022: The 11th Joint Conference on Lexical and Computational Semantics.
• The Beyond the Imitation Game Benchmark. Forthcoming.
• [PDF][Code] Mario Giulianelli, Arabella Sinclair, Raquel Fernández. 2021. Is Information Density Uniform in Task-Oriented Dialogues? In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021).
• [PDF][Code] Mario Giulianelli and Raquel Fernández. 2021. Analysing Human Strategies of Information Transmission as a Function of Discourse Context. In Proceedings of the 25th Conference on Computational Natural Language Learning (CONLL 2021).
• [PDF][Code] Mario Giulianelli, Andrey Kutuzov, Lidia Pivovarova. 2021. Grammatical Profiling for Semantic Change Detection. In Proceedings of the 25th Conference on Computational Natural Language Learning (CONLL 2021).
• [PDF][Code] Mario Giulianelli, Marco Del Tredici, 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][Code] Andrey Kutuzov and Mario Giulianelli. 2020. UiO-UvA at SemEval-2020 Task 1: Contextualised Embeddings for Lexical Semantic Change Detection. In the Proceedings of the 14th International Workshop on Semantic Evaluation (SemEval 2020).
• [PDF][Code] Ece Takmaz, Mario Giulianelli, Sandro Pezzelle, Arabella Sinclair, Raquel Fernández. 2020. Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020).
• [PDF][Code] Mario Giulianelli, Jacqueline Harding, Florian Mohnert, Dieuwke Hupkes, 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][Code] Mario Giulianelli and Daniel de Kok. 2018. Semi-supervised emotion lexicon expansion with label propagation. Computational Linguistics in the Netherlands Journal 8 (CLIN).

Not peer-reviewed

• [PDF] Lexical Semantic Change Analysis with Contextualised Word Representations. 2019. Master’s thesis.
• [PDF] Semi-supervised emotion lexicon expansion with label propagation and specialized word embeddings. 2017. 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.

The only way to predict the future is to invent it.