To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language. The “Bounding Boxes in Text Transformer” (B2T2) also leverages referential information binding words to portions of the image in a single unified architecture. B2T2 is highly effective on the Visual Commonsense Reasoning benchmark, achieving a new state-of-the-art with a 25% relative reduction in error rate compared to published baselines and obtaining the best performance to date on the public leaderboard (as of May 22, 2019). A detailed ablation analysis shows that the early integration of the visual features into the text analysis is key to the effectiveness of the new architecture. A reference implementation of our models is provided.

General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris’ distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task’s training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED

Sequence-to-sequence models with attention have been successful for a variety of NLP problems, but their speed does not scale well for tasks with long source sequences such as document summarization. We propose a novel coarse-to-fine attention model that hierarchically reads a document, using coarse attention to select top-level chunks of text and fine attention to read the words of the chosen chunks. While the computation for training standard attention models scales linearly with source sequence length, our method scales with the number of top-level chunks and can handle much longer sequences. Empirically, we find that while coarse-to-fine attention models lag behind state-of-the-art baselines, our method achieves the desired behavior of sparsely attending to subsets of the document for generation.