About me
Hello world 👋
I’m a Research Engineer at the Barcelona Supercomputing Center. I obtained my PhD in Computational Linguistics at Universitat Pompeu Fabra under the joint supervision of Gemma Boleda and Laia Mayol.
I like teaching
Figure 1. Assessment by Master’s Students in Computational Semantics 👇
Figure 2. Assessment by Undergraduate Students in Information and Communications Technology Course 👇
News
- July 20 to July 25, 2025: I will attend the seminar "Linguistics and Language Models: What Can They Learn from Each Other?" at Schloss Dagstuhl – Leibniz-Zentrum für Informatik in Germany.
- Sept 20th, 2024: Our paper "Training and Fine-Tuning NMT Models for Low-Resource Languages using Apertium-Based Synthetic Corpora" was accepted by WMT2024.
- Sept, 2024: I co-supervised two Master's dissertations, by Meinan Liu and Zizhe Wang, with Bonnie Webber at the School of Informatics, University of Edinburgh.
- June 13th, 2024: Our new paper "Investigating the translation capabilities of Large Language Models trained on parallel data only" is out [Paper]
- May 8th: Our article Comparing models of pronoun production and interpretation via observational and experimental evidence is now available at Glossa: a journal of general linguistics.
- April 29th, 2024: I'm proud to have defended my PhD thesis with an E x c e l l e n t c u m l a u d e . Many thanks to Professors Andrew Kehler, Jennifer Arnold, and Yufang Hou for their valuable input on my committee, and to my supervisors, Gemma Boleda and Laia Mayol, for their guidance and support throughout these four years!
- April 19th, 2024: I gave a talk at the CORE workshop.
- April 5th, 2024: Paper accepted at CogSci 2024: How does grammatical category influence conceptual categorization: The case of Chinese classifiers, with Jialing Liang.
- April 2nd, 2024: I started working as a Research Engineer at the Barcelona Supercomputing Center - Centro Nacional de Supercomputación.
- March 17th - 22nd, 2024: Attended the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024) in Malta. Our work was presented by Yunfang Dong in both the main conference and the 5th Workshop on Computational Approaches to Discourse.
- March 9th, 2024: Xixian Liao, Gemma Boleda, Hannah Rohde, Laia Mayol (accepted). Comparing models of pronoun production and interpretation via observational and experimental evidence. Glossa: a journal of general linguistics.
- January 18th, 2024: Paper accepted at the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024): Syntactic Preposing and Discourse Relations, with Yunfang Dong and Bonnie Webber. And accepted to the main conference!
- December 17th, 2023: I sumbitted my PhD thesis which explores the relationship between referent predictability and pronoun production via a series of novel, primarily computational, approaches--analyses of richly annotated corpora in NLP research, an online corpus passage continuation task with human participants, derivation of predictability estimates from a fine-tuned neural network model, and a Bayesian meta-analysis. My thesis defense will take place on April 29th, 2024. Huge thanks to Professor Andrew Kehler, Professor Jennifer Arnold, and Professor Yufang Hou for agreeing to be on my committee and making the trip to Barcelona for my defense!
- December 6th to 7th, 2023: Poster presentation at the SIGNLL Conference on Computational Natural Language Learning (CoNLL) 2023 with Gemma Boleda in Singapore!
- October 6th, 2023: Paper accepted at the SIGNLL Conference on Computational Natural Language Learning (CoNLL) 2023: The Impact of Familiarity on Naming Variation: A Study on Object Naming in Mandarin Chinese, with Yunke He, Jialing Liang, and Gemma Boleda.
- August 24th, 2023: I co-supervised Yunfang Dong's Master's dissertation with Bonnie Webber. Program: MSc in Speech and Language Processing, School of Philosophy, Psychology & Language Science, University of Edinburgh.
- June 30th to July 3rd, 2023: We organized a 2nd retreat for PhD students in Tarragona, Spain! [REST-CL 2023]
- March 10th, 2023: Poster presentation at Human Sentence Processing 2023, at the University of Pittsburgh!
- Jan 29th, 2023: Abstract accepted at Human Sentence Processing 2023: Bayesian pronoun interpretation in English corpus passage completions, with Laia Mayol and Hannah Rohde!
- August 8th to 19th, 2022: In Galway, Ireland, I served as an ESSLLI Student Session co-chair (track: Language and Computation)!
- May 31st to July 31st, 2022: research stay at the University of Edinburgh!
- June 15th, 2022: Talk at PSYCHOLINGUISTICS COFFEE: Predictability and pronoun production: an online passage continuation study and a Bayesian meta-analysis (two studies in progress), at the University of Edinburgh!
- April 11th to 14th: We organized a retreat for PhD students in Sant Pere de Vilamajor, Catalunya! [REST-CL]
- December 22nd, 2021: Talk at Deep Learning Barcelona Symposium (DLBCN) 2021! [recording]
- November 12th, 2021: Presentation at Workshop UR-Ling 2021!
- November 11th, 2021: Poster presentation at the SIGNLL Conference on Computational Natural Language Learning (CoNLL) 2021!
- September 9th, 2021: Talk at Sinn und Bedeutung (SuB) 26!
- August 31st, 2021: Paper accepted at the SIGNLL Conference on Computational Natural Language Learning (CoNLL) 2021: Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution, with Laura Aina, Gemma Boleda and Matthijs Westera. [PDF]
- August 10th, 2021: Presentation at Workshop on Computational and Experimental Explanations in Semantics and Pragmatics in 32nd European Summer School in Logic, Language and Information (ESSLLI) 2021
- August 6th, 2021: Long presentation at Student Session in 32nd European Summer School in Logic, Language and Information (ESSLLI) 2021:" Coherence-driven predictability and referential form: evidence from English corpus data"
- June 17th, 2021: I completed my service as a moderator for GLiF seminar in the academic year 2020-2021, together with Sebastian Buchczyk. It was really a great honor to have organized so many inspirational talks. Thanks to all our invited speakers!
- June 6th, 2021: Paper accepted at Sinn und Bedeutung 26: Coherence-driven predictability and referential form: evidence from English corpus data, with my supervisors Gemma Boleda and Laia Mayol
- December 17th, 2020: Talk at GLiF seminar, Barcelona, Spain
Our retreat for PhD students in Computational Linguistics REST-CL 2022 ended today. Thank you to our mentors @mormaldo, @CarcassiFausto: we are very grateful for your advice. We go home with new friends and research ideas. We look forward to next editions! pic.twitter.com/u2iGpL9KmS
— COLTupf (@colt_upf) April 14, 2022
Side project
A side project before I finish/quit my PhD…