Projects per year
Abstract / Description of output
Language models have become nearly ubiquitous innatural 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 there presentations 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 |
Editors | Radek Skarnitzl, Jan Volín |
Place of Publication | Prague |
Publisher | Guarant International |
Pages | 1454-1458 |
ISBN (Electronic) | 9788090811423 |
Publication status | Published - 10 Aug 2023 |
Event | 20th International Conference of Phonetic Sciences (ICPhS) - Prague Congress Centre, Prague, Czech Republic Duration: 7 Aug 2023 → 11 Aug 2023 https://www.icphs2023.org/ |
Conference
Conference | 20th International Conference of Phonetic Sciences (ICPhS) |
---|---|
Abbreviated title | ICPhS 2023 |
Country/Territory | Czech Republic |
City | Prague |
Period | 7/08/23 → 11/08/23 |
Internet address |
Keywords / Materials (for Non-textual outputs)
- language model
- BERT
- prosody
- prominence
- part-of-speech
Fingerprint
Dive into the research topics of 'What does BERT learn about prosody?'. Together they form a unique fingerprint.Projects
- 1 Finished