Daniel Hewlett


Coarse-to-Fine Question Answering for Long Documents
Eunsol Choi | Daniel Hewlett | Jakob Uszkoreit | Illia Polosukhin | Alexandre Lacoste | Jonathan Berant
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We present a framework for question answering that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models. While most successful approaches for reading comprehension rely on recurrent neural networks (RNNs), running them over long documents is prohibitively slow because it is difficult to parallelize over sequences. Inspired by how people first skim the document, identify relevant parts, and carefully read these parts to produce an answer, we combine a coarse, fast model for selecting relevant sentences and a more expensive RNN for producing the answer from those sentences. We treat sentence selection as a latent variable trained jointly from the answer only using reinforcement learning. Experiments demonstrate state-of-the-art performance on a challenging subset of the WikiReading dataset and on a new dataset, while speeding up the model by 3.5x-6.7x.

Accurate Supervised and Semi-Supervised Machine Reading for Long Documents
Daniel Hewlett | Llion Jones | Alexandre Lacoste | Izzeddin Gur
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We introduce a hierarchical architecture for machine reading capable of extracting precise information from long documents. The model divides the document into small, overlapping windows and encodes all windows in parallel with an RNN. It then attends over these window encodings, reducing them to a single encoding, which is decoded into an answer using a sequence decoder. This hierarchical approach allows the model to scale to longer documents without increasing the number of sequential steps. In a supervised setting, our model achieves state of the art accuracy of 76.8 on the WikiReading dataset. We also evaluate the model in a semi-supervised setting by downsampling the WikiReading training set to create increasingly smaller amounts of supervision, while leaving the full unlabeled document corpus to train a sequence autoencoder on document windows. We evaluate models that can reuse autoencoder states and outputs without fine-tuning their weights, allowing for more efficient training and inference.


WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia
Daniel Hewlett | Alexandre Lacoste | Llion Jones | Illia Polosukhin | Andrew Fandrianto | Jay Han | Matthew Kelcey | David Berthelot
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


Word Segmentation as General Chunking
Daniel Hewlett | Paul Cohen
Proceedings of the Fifteenth Conference on Computational Natural Language Learning

Fully Unsupervised Word Segmentation with BVE and MDL
Daniel Hewlett | Paul Cohen
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies