English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Pre-trained language models (PLMs) demonstrate excellent abilities tounderstand texts in the generic domain while struggling in a specific domain.Although continued pre-training on a large domain-specific corpus is effective,it is costly to tune all the parameters on the domain. In this paper, weinvestigate whether we can adapt PLMs both effectively and efficiently by onlytuning a few parameters. Specifically, we decouple the feed-forward networks(FFNs) of the Transformer architecture into two parts: the original pre-trainedFFNs to maintain the old-domain knowledge and our novel domain-specificadapters to inject domain-specific knowledge in parallel. Then we adopt amixture-of-adapters gate to fuse the knowledge from different domain adaptersdynamically. Our proposed Mixture-of-Domain-Adapters (MixDA) employs atwo-stage adapter-tuning strategy that leverages both unlabeled data andlabeled data to help the domain adaptation: i) domain-specific adapter onunlabeled data; followed by ii) the task-specific adapter on labeled data.MixDA can be seamlessly plugged into the pretraining-finetuning paradigm andour experiments demonstrate that MixDA achieves superior performance onin-domain tasks (GLUE), out-of-domain tasks (ChemProt, RCT, IMDB, Amazon), andknowledge-intensive tasks (KILT). Further analyses demonstrate the reliability,scalability, and efficiency of our method. The code is available athttps://github.com/Amano-Aki/Mixture-of-Domain-Adapters.

Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories