Dec 14, 2014 · We show that a novel but simple feature embedding approach provides better performance, by exploiting the feature template structure common in ...

Yi Yang and Jacob Eisenstein. 2015. Unsupervised Multi-Domain Adaptation with Feature Embeddings. In Proceedings of the 2015 Conference of the North American ...

It is shown that a novel but simple feature embedding approach provides better performance, by exploiting the feature template structure common in NLP ...

We show that a novel but simple feature embedding approach provides better performance, by exploiting the feature template structure common in NLP problems.

In this work, we propose a method of Domain-. Aware Feature Embedding (DAFE) that performs unsupervised domain adaptation by disentangling representations into ...

Aug 27, 2019 · In this work, we propose an approach that adapts models with domain-aware feature embeddings, which are learned via an auxiliary language ...

In this work, we propose a method of Domain-. Aware Feature Embedding (DAFE) that performs unsupervised domain adaptation by disentangling representations into ...

Our Domain2Vec includes two components: we first leverage feature disentanglement to generate the domain- specific features, and then we achieve deep domain ...

Unsupervised Multi-Domain Adaptation with Feature Embeddings. HLT 2015 · Jacob Eisenstein, Yi Yang · Edit social preview.

In this work we introduce a novel deep learning framework which unifies different paradigms in unsupervised domain adaptation. Specifically, we propose domain ...