What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10426960" target="_blank" >RIV/00216208:11320/20:10426960 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/2020.findings-emnlp.389" target="_blank" >https://www.aclweb.org/anthology/2020.findings-emnlp.389</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models
Original language description
Peeking into the inner workings of BERT has shown that its layers resemble the classical NLP pipeline, with progressively more complex tasks being concentrated in later layers. To investigate to what extent these results also hold for a language other than English, we probe a Dutch BERT-based model and the multilingual BERT model for Dutch NLP tasks. In addition, through a deeper analysis of part-of-speech tagging, we show that also within a given task, information is spread over different parts of the network and the pipeline might not be as neat as it seems. Each layer has different specialisations, so that it may be more useful to combine information from different layers, instead of selecting a single one based on the best overall performance.
Czech name
—
Czech description
—
Classification
Type
O - Miscellaneous
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů