| Autor: |
Tanti, M, van der Plas, L, Borg, C, Gatt, A, Bastings, Jasmijn, Belinkov, Yonatan, Dupoux, Emmanuel, Giulianelli, Mario, Hupkes, Dieuwke, Pinter, Yuval, Sajjad, Hassan |
| Přispěvatelé: |
Sub Natural Language Processing, Natural Language Processing |
| Jazyk: |
angličtina |
| Rok vydání: |
2021 |
| Předmět: |
|
| Popis: |
Recent work has shown evidence that the knowledge acquired by multilingual BERT (mBERT) has two components: a language-specific and a language-neutral one. This paper analyses the relationship between them, in the context of fine-tuning on two tasks – POS tagging and natural language inference – which require the model to bring to bear different degrees of language-specific knowledge. Visualisations reveal that mBERT loses the ability to cluster representations by language after fine-tuning, a result that is supported by evidence from language identification experiments. However, further experiments on ‘unlearning’ language-specific representations using gradient reversal and iterative adversarial learning are shown not to add further improvement to the language-independent component over and above the effect of fine-tuning. The results presented here suggest that the process of fine-tuning causes a reorganisation of the model’s limited representational capacity, enhancing language-independent representations at the expense of language-specific ones. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
