• Publications
  • Influence
Bidirectional Attention Flow for Machine Comprehension
The BIDAF network is introduced, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization. Expand
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
A fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints, which outperforms all the current efficient CNN networks such as MobileNet, ShuffleNet, and ENet on both standard metrics and the newly introduced performance metrics that measure efficiency on edge devices. Expand
Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links and supports construction of a scientific knowledge graph, which is used to analyze information in scientific literature. Expand
Learning to Solve Arithmetic Word Problems with Verb Categorization
The paper analyzes the arithmetic-word problems “genre”, identifying seven categories of verbs used in such problems, and reports the first learning results on this task without reliance on predefined templates and makes the data publicly available. Expand
UnifiedQA: Crossing Format Boundaries With a Single QA System
This work uses the latest advances in language modeling to build a single pre-trained QA model, UNIFIEDQA, that performs well across 19 QA datasets spanning 4 diverse formats, and results in a new state of the art on 10 factoid and commonsense question answering datasets. Expand
Entity, Relation, and Event Extraction with Contextualized Span Representations
This work examines the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction (called DyGIE++) and achieves state-of-the-art results across all tasks. Expand
ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network
We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wiseExpand
Text Generation from Knowledge Graphs with Graph Transformers
This work addresses the problem of generating coherent multi-sentence texts from the output of an information extraction system, and in particular a knowledge graph by introducing a novel graph transforming encoder which can leverage the relational structure of such knowledge graphs without imposing linearization or hierarchical constraints. Expand
A general framework for information extraction using dynamic span graphs
This framework significantly outperforms state-of-the-art on multiple information extraction tasks across multiple datasets reflecting different domains and is good at detecting nested span entities, with significant F1 score improvement on the ACE dataset. Expand
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
A new graph-based recurrent retrieval approach that learns to retrieve reasoning paths over the Wikipedia graph to answer multi-hop open-domain questions and achieves significant improvement in HotpotQA, outperforming the previous best model by more than 14 points. Expand