Papers by Gosse Bouma
Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing multilingual models cannot fully leverage training data when it is available in different task-language combinations. |
| Approach: | They propose a single hypernetwork that unifies multi-task and multilingual learning with efficient adaptation. |
| Outcome: | The proposed model achieves the best or competitive gain when a mixture of multiple resources is available while being significantly more efficient than existing models. |
PoS Tagging, Lemmatization and Dependency Parsing of West Frisian (2022.lrec-1)
Copied to clipboard
Wilbert Heeringa, Gosse Bouma, Martha Hofman, Jelle Brouwer, Eduard Drenth, Jan Wijffels, Hans Van de Velde
| Challenge: | a lemmatizer/PoS tagger/dependency parser for west frisian is released as a web app and as . web service. |
| Approach: | They propose a lemmatizer/PoS tagger/dependency parser for West Frisian using a corpus of 44,714 words in 3,126 sentences that were annotated according to the guidelines of Universal Dependencies version 2. |
| Outcome: | The proposed lemmatizer/PoS tagger/dependency parser performs better than the previous version of Oersetter . the current corpus contains 44,714 words in 3,126 sentences . |
UDapter: Language Adaptation for Truly Universal Dependency Parsing (2020.emnlp-main)
Copied to clipboard
| Challenge: | Cross-language interference and restrained model capacity remain major obstacles in multilingual dependency parsing. |
| Approach: | They propose a multilingual task adaptation approach based on contextual parameter generation and adapter modules that learn adapters via language embeddings while sharing model parameters across languages. |
| Outcome: | The proposed approach outperforms strong monolingual and multilingual baselines on most languages on high-resource and low-resourced (zero-shot) languages. |