Machines That Read Harry Potter

Software That Reads Harry Potter Might Perform Some Wizardry

Maluuba is training deep-learning algorithms to answer questions about small amounts of text. The technology might eventually read user manuals so you don’t have to.

Will Knight | March 28, 2016

Teaching a computer to play Go at a superhuman level is cool, but not especially useful for you or me. But what if a computer could read a few dozen pages of text, like the manual for a new microwave, and then answer questions about how it works? Sign me up.
Reading and comprehending text is incredibly difficult for computers, but a Canadian company called Maluuba has made progress with an algorithm that can read text and answer questions about it with impressive accuracy. Most importantly, unlike other approaches, it works with just small amounts of text. It might eventually help computers “comprehend” documents.

Source: http://www.maluuba.com/

<more at https://www.technologyreview.com/s/601066/software-that-reads-harry-potter-might-perform-some-wizardry/; related links and articles: http://www.maluuba.com/ (Maluba website) and http://arxiv.org/abs/1603.08884v1 (A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data. Adam Trischler, Zheng Ye, Xingdi Yuan, Jing He, Phillip Bachman, and Kaheer Suleman. arXiv:1603.08884 [cs.CL]. [Abstract: Understanding unstructured text is a major goal within natural language processing. Comprehension tests pose questions based on short text passages to evaluate such understanding. In this work, we investigate machine comprehension on the challenging {\it MCTest} benchmark. Partly because of its limited size, prior work on {\it MCTest} has focused mainly on engineering better features. We tackle the dataset with a neural approach, harnessing simple neural networks arranged in a parallel hierarchy. The parallel hierarchy enables our model to compare the passage, question, and answer from a variety of trainable perspectives, as opposed to using a manually designed, rigid feature set. Perspectives range from the word level to sentence fragments to sequences of sentences; the networks operate only on word-embedding representations of text. When trained with a methodology designed to help cope with limited training data, our Parallel-Hierarchical model sets a new state of the art for {\it MCTest}, outperforming previous feature-engineered approaches slightly and previous neural approaches by a significant margin (over 15\% absolute).])>