filmov
tv
Computational Linguistics in Bulgaria 2024: MAIN CONFERENCE (9 September 2024)
![preview_player](https://i.ytimg.com/vi/r7P0I3iTgjk/maxresdefault.jpg)
Показать описание
PROGRAMME
9 September 2024
8:30 – Registration
9:00 – 9:15 – Conference Opening
Neural Networks, Large Language Models and Language Modelling
9:15 – 10:00 – Plenary Talk: Dr. Veselin Stoyanov (TOME AI, USA): Large Language Models for the Real World: Explorations of Sparse, Cross-lingual Understanding and Instruction-Tuned LLMs
10:00 – 11:15 – Session 1: Large Language Models and Language Learning | Chair: Stoyan Mihov (Institute of Information and Communication Technologies, BAS)
10:00 – 10:25 – Radu Ion, Verginica Barbu Mititelu, Vasile Pais, Elena Irimia, Valentin Badea: A Cross–model Study on Learning Romanian Parts of Speech with Transformer Models
10:25 – 10:50 – Ekaterina Goliakova, David Langlois: What do BERT Word Embeddings Learn about the French Language?
10:50 – 11:15 – Camille Lavigne, Alex Stasica: Whisper–TAD: A General Model for Transcription, Alignment and Diarization of Speech
11:15 – 11:30 – Coffee Break
11:30 – 12:45 – Session 2: Large Language Models in Analysis and Generation | Chair: Ivan Koychev (Sofia University St. Kliment Ohridski)
11:30 – 11:55 – Iglika Nikolova–Stoupak, Gael Lejeune, Eva Schaeffer–Lacroix: Contemporary LLMs and Literary Abridgement: An Analytical Inquiry
11:55 – 12:20 – Milica Ikonic Nesic, Sasa Petalinkar, Mihailo Skoric, Ranka Stankovic, Biljana Rujevic: Advancing Sentiment Analysis in Serbian Literature: A Zero and Few–Shot Learning Approach Using the Mistral Model
12:20 – 12:45 – Lyuboslav Karev, Ivan Koychev: Generating Phonetic Embeddings for Bulgarian Words with Neural Networks
12:45 – 13:45 – Lunch and Poster Session
13:45 – 14:30 – Plenary Talk: Prof. Joakim Nivre (Uppsala University and RISE, Sweden): Ten Years of Universal Dependencies
14:30 – 15:45 – Session 3: Treebanks and Parsers in Universal Dependencies | Chair: Milena Dobreva (University of Strathclyde)
14:30 – 14:55 – Nelda Kote, Rozana Rushiti, Anila Cepani, Alba Haveriku, Evis Trandafili, Elinda Kajo Mece, Elsa Skenderi Rakipllari, Lindita Xhanari, Albana Deda: Universal Dependencies Treebank for Standard Albanian: A New Approach
14:55 – 15:20 – Verginica Barbu Mititelu, Tudor Voicu: Function Multiword Expressions Annotated with Discourse Relations in the Romanian Reference Treebank
15:20 – 15:45 – Atanas Atanasov: Dependency Parser for Bulgarian
15:45 – 16:00 – Coffee Break
16:00 – 17:40 – Session 4: Modeling Multiword Expressions | Chair: Aleksandra Bagasheva (Sofia University St. Kliment Ohridski)
16:00 – 16:25 – Madalina Chitez, Ana–Maria Bucur, Andreea Dinca, Roxana Rogobete: Towards a Romanian Phrasal Academic Lexicon
16:50 – 17:15 – Laura Occhipinti: Complex Word Identification for Italian Language: A Dictionary–based Approach
17:15 – 17:40 – Ivana Brac, Matea Birtic: Verbal Multiword Expressions in the Croatian Verb Lexicon
9 September 2024
8:30 – Registration
9:00 – 9:15 – Conference Opening
Neural Networks, Large Language Models and Language Modelling
9:15 – 10:00 – Plenary Talk: Dr. Veselin Stoyanov (TOME AI, USA): Large Language Models for the Real World: Explorations of Sparse, Cross-lingual Understanding and Instruction-Tuned LLMs
10:00 – 11:15 – Session 1: Large Language Models and Language Learning | Chair: Stoyan Mihov (Institute of Information and Communication Technologies, BAS)
10:00 – 10:25 – Radu Ion, Verginica Barbu Mititelu, Vasile Pais, Elena Irimia, Valentin Badea: A Cross–model Study on Learning Romanian Parts of Speech with Transformer Models
10:25 – 10:50 – Ekaterina Goliakova, David Langlois: What do BERT Word Embeddings Learn about the French Language?
10:50 – 11:15 – Camille Lavigne, Alex Stasica: Whisper–TAD: A General Model for Transcription, Alignment and Diarization of Speech
11:15 – 11:30 – Coffee Break
11:30 – 12:45 – Session 2: Large Language Models in Analysis and Generation | Chair: Ivan Koychev (Sofia University St. Kliment Ohridski)
11:30 – 11:55 – Iglika Nikolova–Stoupak, Gael Lejeune, Eva Schaeffer–Lacroix: Contemporary LLMs and Literary Abridgement: An Analytical Inquiry
11:55 – 12:20 – Milica Ikonic Nesic, Sasa Petalinkar, Mihailo Skoric, Ranka Stankovic, Biljana Rujevic: Advancing Sentiment Analysis in Serbian Literature: A Zero and Few–Shot Learning Approach Using the Mistral Model
12:20 – 12:45 – Lyuboslav Karev, Ivan Koychev: Generating Phonetic Embeddings for Bulgarian Words with Neural Networks
12:45 – 13:45 – Lunch and Poster Session
13:45 – 14:30 – Plenary Talk: Prof. Joakim Nivre (Uppsala University and RISE, Sweden): Ten Years of Universal Dependencies
14:30 – 15:45 – Session 3: Treebanks and Parsers in Universal Dependencies | Chair: Milena Dobreva (University of Strathclyde)
14:30 – 14:55 – Nelda Kote, Rozana Rushiti, Anila Cepani, Alba Haveriku, Evis Trandafili, Elinda Kajo Mece, Elsa Skenderi Rakipllari, Lindita Xhanari, Albana Deda: Universal Dependencies Treebank for Standard Albanian: A New Approach
14:55 – 15:20 – Verginica Barbu Mititelu, Tudor Voicu: Function Multiword Expressions Annotated with Discourse Relations in the Romanian Reference Treebank
15:20 – 15:45 – Atanas Atanasov: Dependency Parser for Bulgarian
15:45 – 16:00 – Coffee Break
16:00 – 17:40 – Session 4: Modeling Multiword Expressions | Chair: Aleksandra Bagasheva (Sofia University St. Kliment Ohridski)
16:00 – 16:25 – Madalina Chitez, Ana–Maria Bucur, Andreea Dinca, Roxana Rogobete: Towards a Romanian Phrasal Academic Lexicon
16:50 – 17:15 – Laura Occhipinti: Complex Word Identification for Italian Language: A Dictionary–based Approach
17:15 – 17:40 – Ivana Brac, Matea Birtic: Verbal Multiword Expressions in the Croatian Verb Lexicon