Exploring Italian sentence embeddings properties through multi-tasking
This work addresses the understanding of linguistic representation in LLMs for Italian, but it is incremental as it builds on existing methods and datasets.
The study investigated whether pre-trained language models encode abstract linguistic information like syntax and semantics in Italian sentence embeddings using multi-task learning on synthetic data, finding that different tasks rely on distinct aspects of the embeddings rather than shared abstract structures.
We investigate to what degree existing LLMs encode abstract linguistic information in Italian in a multi-task setting. We exploit curated synthetic data on a large scale -- several Blackbird Language Matrices (BLMs) problems in Italian -- and use them to study how sentence representations built using pre-trained language models encode specific syntactic and semantic information. We use a two-level architecture to model separately a compression of the sentence embeddings into a representation that contains relevant information for a task, and a BLM task. We then investigate whether we can obtain compressed sentence representations that encode syntactic and semantic information relevant to several BLM tasks. While we expected that the sentence structure -- in terms of sequence of phrases/chunks -- and chunk properties could be shared across tasks, performance and error analysis show that the clues for the different tasks are encoded in different manners in the sentence embeddings, suggesting that abstract linguistic notions such as constituents or thematic roles does not seem to be present in the pretrained sentence embeddings.