Published November 1, 2023 | Version v1
Conference paper Open

Assessment of Pre-Trained Models Across Languages and Grammars

Authors/Creators

  • 1. ROR icon Universidade da Coruña

Abstract (English)

We present an approach for assessing how multilingual large language models (LLMs) learn syntax in terms of multi-formalism syntactic structures. We aim to recover constituent and dependency structures by casting parsing as sequence labeling. To do so, we select a few LLMs and study them on 13 diverse UD treebanks for dependency parsing and 10 treebanks for constituent parsing. Our results show that: (i) the framework is consistent across encodings, (ii) pre-trained word vectors do not favor constituency representations of syntax over dependencies, (iii) sub-word tokenization is needed to represent syntax, in contrast to character-based models, and (iv) occurrence of a language in the pretraining data is more important than the amount of task data when recovering syntax from the word vectors.

Other (English)

We acknowledge the European Research Council (ERC), which has funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615), ERDF/MICINN-AEI (SCANNER-UDC, PID2020-113230RB-C21), Xunta de Galicia (ED431C 2020/11), grant FPI 2021 (PID2020-113230RB-C21) funded by MCIN/AEI/10.13039/501100011033, and Centro de Investigación de Galicia “CITIC”, funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS).

Files

Muñoz_Ortiz_2023_Assessment_pre-trained_models_across_lang_gram.pdf

Files (2.0 MB)

Additional details

Identifiers

Handle
2183/36572