Reading Wikipedia to Answer Open-Domain Questions

This paper proposes to tackle open-domain question answering using Wikipedia
as the unique knowledge source: the answer to any factoid question is a text
span in a Wikipedia article. This task of machine reading at scale combines the
challenges of document retrieval – finding the relevant articles – with that of
machine comprehension of text – identifying the answer spans from those
articles. Our approach combines a search component based on bigram hashing and
TF-IDF matching with a multi-layer recurrent neural network model trained to
detect answers in Wikipedia paragraphs. Our experiments on multiple existing QA
datasets indicate that (1) both modules are highly competitive with respect to
existing counterparts and (2) multitask learning using distant supervision on
their combination is an effective complete system on this challenging task.


No Comments

Leave a Reply

AllSaints September 2017 Men’s Lookbook


Government ministers travel to Nordic countries and Asia to promote UK tech

Karen Bradley will travel to Finland and Sweden to promote the digital economy, while Matt Hancock will push UK cyber security in Asia…In Tech start-up news Source:

A Lightroom Tip on Impromptu Slideshows I Did Not Know (and a brief Hurricane Irma update)

OK, I knew the first part of Benjamin’s tip, but I have to admit, I did NOT know the 2nd part (where he chooses the template). This is really good stuff! Quick Hurricane Irma Update We’re all OK!!! In fact, somehow we made it through in flying colors – didn’t …