Arianna Bisazza, A. Ustun, G. Bouma, Gertjan van Noord
We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| ahmetustun/udapter | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| AdapterWithParameterGen | Ran | ahmetustun/udapter/adapter_bert/modeling.py code served (permissive licence) · get_code("bdee1211308ce512") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, crosslanguage interference and restrained model capacity remain major obstacles. To address this, we propose a novel multilingual task adaptation approach based on contextual parameter generation and adapter modules. This approach enables to learn adapters via language embeddings while sharing model parameters across languages. It also allows for an easy but effective integration of existing linguistic typology features into the parsing network. The resulting parser, UDapter, outperforms strong monolingual and multilingual baselines on the majority of both high-resource and lowresource (zero-shot) languages, showing the success of the proposed adaptation approach. Our in-depth analyses show that soft parameter sharing via typological features is key to this success. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.14327")
get_code_for_paper("2004.14327")
have("2004.14327")
Connect an agent — have() is free.