{"url":"/method/emea","slug":"emea","name":"EMEA","full_name":"Entropy Minimized Ensemble of Adapters","full_name_withheld":false,"description_markdown":"**Entropy Minimized Ensemble of Adapters**, or **EMEA**, is a method that optimizes the ensemble weights of the pretrained language adapters for each test sentence by minimizing the entropy of its predictions. The intuition behind the method is that a good [adapter](https://paperswithcode.com/method/adapter) weight $\\alpha$ for a test input $x$ should make the model more confident in its prediction for $x$, that is, it should lead to lower model entropy over the input","description_state":"present","introduced_year":null,"introduced_by":{"title":"Efficient Test Time Adapter Ensembling for Low-resource Language Varieties","paper":"/paper/efficient-test-time-adapter-ensembling-for","first_author":"Xinyi Wang","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/efficient-test-time-adapter-ensembling-for"},"source":{"url":"https://arxiv.org/abs/2109.04877v1","title":"Efficient Test Time Adapter Ensembling for Low-resource Language Varieties","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Ensembling","url":"/methods/category/ensembling","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/non-parametric-online-learning-from-human","title":"Non-Parametric Online Learning from Human Feedback for Neural Machine Translation","date":"2021-09-23","arxiv_id":"2109.11136","n_code_links":1,"syntology":{"ran":5,"of":8,"unverified":3,"pointer_only":8}},{"paper":"/paper/efficient-test-time-adapter-ensembling-for","title":"Efficient Test Time Adapter Ensembling for Low-resource Language Varieties","date":"2021-09-10","arxiv_id":"2109.04877","n_code_links":1,"syntology":null}],"papers_shown":2,"tasks":[{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":1},{"task":"/task/machine-translation","name":"Machine Translation","papers":1},{"task":"/task/nmt","name":"NMT","papers":1},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":1},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":1},{"task":"/task/part-of-speech-tagging","name":"Part-Of-Speech Tagging","papers":1},{"task":"/task/sentence","name":"Sentence","papers":1},{"task":"/task/translation","name":"Translation","papers":1},{"task":"/task/named-entity-recognition","name":"named-entity-recognition","papers":1},{"task":"/task/parameter-efficient-fine-tuning","name":"parameter-efficient fine-tuning","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2021","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/emea"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}