Papers by Alan Ansell
Composable Sparse Fine-Tuning for Cross-Lingual Transfer (2022.acl-long)
Copied to clipboard
| Challenge: | Adapters and sparse fine-tuning have been developed to improve transfer learning . a number of approaches have been proposed to improve performance of fine-untuners . |
| Approach: | They propose a method that fine-tunes the entire set of parameters of a large pretrained model . they use adapters and sparse fine-uning to improve model efficiency . |
| Outcome: | The proposed method outperforms adapters in cross-lingual transfer benchmarks. |
MAD-G: Multilingual Adapter Generation for Efficient Cross-Lingual Transfer (2021.findings-emnlp)
Copied to clipboard
Alan Ansell, Edoardo Maria Ponti, Jonas Pfeiffer, Sebastian Ruder, Goran Glavaš, Ivan Vulić, Anna Korhonen
| Challenge: | Massively multilingual transformers (MMTs) have benefited from additional training of language-specific adapters, but this approach is not viable for the vast majority of languages due to limitations in their corpus size or compute budgets. |
| Approach: | They propose a multilingual ADapter generation approach which contextually generates language adapters from language representations based on typological features. |
| Outcome: | The proposed method improves cross-lingual transfer performance on part-of-speech tagging, dependency parsing, and named entity recognition tasks while remaining cost-effective. |
PolyLM: Learning about Polysemy through Language Modeling (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to embed word senses have been overtaken by contextualized embeddings . alan ansell and jim koenig present a method which can be applied to downstream tasks . |
| Approach: | They propose a method which formulates learning sense embeddings as a language modeling problem. |
| Outcome: | The proposed method performs better than existing sense embedding methods on WSI tasks . it matches the current state-of-the-art specialized WSi method despite having six times fewer parameters . |
Distilling Efficient Language-Specific Models for Cross-Lingual Transfer (2023.findings-acl)
Copied to clipboard
| Challenge: | Massively multilingual Transformers (MMTs) are widely used for cross-lingual transfer learning. |
| Approach: | They propose to extract compressed, language-specific models from MMTs which retain the capacity of the original MMT for cross-lingual transfer. |
| Outcome: | The proposed model outperforms models trained from scratch in zero-shot cross-lingual transfer across benchmarks. |
Unifying Cross-Lingual Transfer across Scenarios of Resource Scarcity (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to deal with resource scarcity have not been developed to deal effectively with the problem. |
| Approach: | They propose to use a set of tools to harness data from one or more high-resource "source" languages to compensate for a shortage of data in low-resourced "target" languages. |
| Outcome: | The proposed technique can be easily adapted to unseen languages, extending the range of the proposed technique and translation-based transfer more broadly. |
Cross-Lingual Transfer with Target Language-Ready Task Adapters (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks for (zero-shot) cross-lingual transfer employ separate language and task adapters which can be arbitrarily combined to perform any task to any target language. |
| Approach: | They propose to fine-tune 'target language-ready' adapters to the target language to achieve better transfer performance without sacrificing the modularity of MAD-X. |
| Outcome: | The proposed adapters outperform MAD-X and BAD-X on most tasks and languages while maintaining the modularity of MAD. |