Adapter Modules

AbstractRecent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address …...

AbstractState-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model. However, such modules are trained separately for each task and thus do not …...

AbstractAdapter modules enable modular and efficient zero-shot cross-lingual transfer, where current state-of-the-art adapter-based approaches learn specialized language adapters (LAs) for individual languages. In this work, we show that it is …...

AbstractDeploying task-oriented dialog ToD systems for new domains and tasks requires natural language understanding models that are 1) resource-efficient and work under low-data regimes; 2) adaptable, efficient, and quick-to-train; 3) …...

AbstractThis paper describes the submissions of the UPC Machine Translation group to the IWSLT 2022 Offline Speech Translation and Speech-to-Speech Translation tracks. The offline task involves translating English speech to …...

AbstractIn this paper, we focus on video-to-text summarization and investigate how to best utilize multimodal information for summarizing long inputs (e.g., an hour-long TV show) into long outputs (e.g., a …...