What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models

Kód výsledku v 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>

Výsledek na webu

<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

—

Jazyk výsledku

angličtina

Název v původním jazyce

What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models

Popis výsledku anglicky

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.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů