Byutilizingmodality dropout during pre-training, we demonstrate that a single fine-tuned model can achieve performance on par or better than the state-of-the-art modality-specific models.

Recentwork has shown that significant gains can be obtained withmodel parallelism, i.e, partitioning a neural network's computational graph onto multiple devices.

A global scoring mechanism isthen developed toregulate beam search togenerate summaries in a near-global optimal fashion.

Using a similarity metric in that multimodal embedding space, we perform mining of audio in German, French, Spanish and English from Librivox against billions of sentences from CommonCrawl.