Abstract
Language models have become nearly ubiquitous in natural language processing applications achieving state-of-the-art results in many tasks including prosody. As the model design does not define predetermined linguistic targets during training but rather aims at learning generalized representations of the language, analyzing and interpreting the representations that models implicitly capture is important in bridging the gap between interpretability and model performance. Several studies have explored the linguistic information that models capture providing some insights on their representational capacity. However, the current studies have not explored whether prosody is part of the structural information of the language that models learn. In this work, we perform a series of experiments on BERT probing the representations captured at different layers. Our results show that information about prosodic prominence spans across many layers but is mostly focused in middle layers suggesting that BERT relies mostly on syntactic and semantic information.
Original language | English |
---|---|
Title of host publication | Proceedings of the 20th International Congress of Phonetic Sciences (ICPhS 2023) |
Editors | Radek Skarnitzl, Jan Volín |
Number of pages | 5 |
Place of Publication | Prague |
Publisher | GUARANT International spol. s r.o. |
Publication date | Aug 2023 |
Pages | 1454-1458 |
ISBN (Electronic) | 9788090811423 |
Publication status | Published - Aug 2023 |
MoE publication type | A4 Article in conference proceedings |
Event | International Congress of Phonetic Sciences - Prague Congress Center, Prague, Czech Republic Duration: 7 Aug 2023 → 11 Aug 2023 Conference number: 20 https://www.icphs2023.org/ |
Fields of Science
- 213 Electronic, automation and communications engineering, electronics
- 113 Computer and information sciences
- 6121 Languages