Адаптивная Настройка Домена

AbstractContextualized word embeddings such as ELMo and BERT provide a foundation for strong performance across a wide range of natural language processing tasks by pretraining on large corpora of unlabeled …...

AbstractWe tackle the task of adapting event extractors to new domains without labeled data, by aligning the marginal distributions of source and target domains. As a testbed, we create two …...