LyS Research Group

Thrilled to have hosted Bharathi Raja Chakravarthi from #UniversityOfGalway at @lysresearch this week! He shared great insights on his #Research into #NLProc for abusive-offensive language detection and low-resource languages. A very inspiring visit! @citicresearch @UDC_gal

💡 #Sustainability in #AI is a shared challenge. We’re excited to keep collaborating toward greener algorithms and responsible NLP! Learn more about the symposium 👉catedrainditexalgoritmosverdes.com/en/green-artif… #GreenAI #NLProc #artificialintelligence

🌍 We’re proud to share our group’s contributions to the #GreenAI Symposium at @citicresearch! Three works exploring #sustainability in #NLProc and #AI were presented. Read on for the highlights 👇 @lysresearch #artificialintelligence

📊 Roi Santos-Ríos presented a poster on reducing AI’s carbon footprint in official statistics. A case study on economic classification for greener data-driven governance. @es_INE @lysresearch #GreenAI #NLProc #DataScience

🌱 David Vilares delivered an oral presentation: “Green Structured Prediction in NLP”. How can structured prediction models become more energy-efficient without sacrificing (too much) performance? #GreenAI #NLProc

🔍 . @OlgaZamaraeva examined syntactic theory to compare human-authored vs. #LLM -generated news texts. Her talk in the #GreenAI TIC Talk session raised interesting questions on how language is used by generative #AI. #NLProc #Syntax @lysresearch

🚀 Our colleague Carlos Gómez @carlosgr_nlp has been included in the World's Top 2% Scientist List by Stanford & Elsevier 🌍 A clear example of how #AI research done in #Galicia can have a global impact 💡✨ bit.ly/4o3pxH9 #NLProc @lysresearch @citicresearch @UDC_gal

👨‍🎓Roi Santos-Ríos at #SEPLN2025 Doctoral Symposium 🎓Advisors: Montse Cuadros & German Rigau 📃Thesis work: Automatic Classification of the Economic Activity of a Company Using ML and DL Techniques #NLProc #NLP @lysresearch @citicresearch @UDC_gal

Here's Roi!

Today researchers Roi Santos-Ríos & Muhammad Imran presented 2 works at IberLEF 2025 #SEPLN2025. "Zero-Shot Code Generation for Spanish Tabular QA" and "Enhancing Transformer-Based Sentiment Analysis for the REST-MEX 2025 Challenge" @lysresearch @citicresearch @UDC_gal #NLProc

Promoting talent! 🎓 @miguel_a_alonso acts as advisor in #SEPLN2025 Doctoral Symposium for PhD students Victoria Muñoz García (working on bias detection and mitigation) and Alba Pérez Montero (working on disinformation detection) #NLProc #NLP @lysresearch

IQTrial integrated management platform for biomed trials was presented at Galician Health Ministry. @JesusVilares @carlosgr_nlp succesfully leaded @lysresearch #NLProc work within IQVIA consortium for #INNOVATRIAL project. @citicresearch @UDC_gal

Today, Adrián Gude, Roi Santos and @anaezquerro_ have presented "LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA" at @semeval_tableQA @SemEvalWorkshop at #ACL2025NLP @lysresearch @citicresearch @UDC_gal

Today (Wed.) @OlgaZamaraeva presents "Comparing LLM-generated and human-authored news text using formal syntactic theory" at #ACL2025NLP Poster Session 4 (Hall 4/5 at 11:00). You're invited! @lysresearch @citicresearch @UDC_gal 🔗Paper aclanthology.org/2025.acl-long.…

Tomorrow (Tuesday) at 14:00 we present "Hierarchical Bracketing Encodings for Dependency Parsing as Tagging" at #ACL2025NLP. Meet @anaezquerro_ @eusondavid @carlosgr_nlp at Room 1.86 @lysresearch @citicresearch @UDC_gal 🔗Paper aclanthology.org/2025.acl-long.…

.@lysresearch group has disembarked at #ACL2025NLP. Keep tuned to know where and when to meet us. #NLProc @citicresearch @UDC_gal

This morning, Asst Prof @RolloFederica from @UNIMORE_univ, who is visiting @lysresearch, gave us a very interesting talk at @FIC_UDC about "Graph-based modeling and optimization of #UrbanMobility" @UDC_gal.

Currently at the Data-oriented Area Studies Unit End-Year Workshop 2025 on "Data-Oriented Approaches to the Social Sciences and Humanities", at @kucseas (Kyoto University), honored to give a talk at 16:40 on "Contrasting linguistic patterns in human and LLM-generated news text".

Our first two days at #EMNLP2024!

Today from 11:00 to 11:15 at the Discourse + Phonology + Syntax Track 2 session (Room Flager), @OlgaZamaraeva will be presenting "Revisiting Supertagging for Faster HPSG Parsing" (with @carlosgr_nlp). 🔗Paper: aclanthology.org/2024.emnlp-mai…