Samsung Research, the advanced R&D hub of Samsung Electronics' SET (end-products) business, has ranked first in two of the world's top global artificial intelligence (AI) machine reading comprehension competitions. Samsung Research recently placed first in the MAchine Reading COmprehension (MS MARCO) Competition held by Microsoft (MS), as well as showing the best performance in TriviaQA* hosted by the University of Washington, proving the excellence of its AI algorithm. With intense competition in developing AI technologies globally, machine reading comprehension competitions such as MS MARCO are booming around the world. MS MARCO and TriviaQA are among the actively researched and used machine reading comprehension competitions along with SQuAD of Stanford University and NarrativeQA of DeepMind. Distinguished universities around the world and global AI firms including Samsung are competing in these challenges.
First, it was the AlphaGo AI from Google's DeepMind subsidiary which beat the world's best Go players at their own game to make a record. Then, an AI named Libratus, developed by the Carnegie Mellon University, outclassed Poker pros in a tournament to turn the world's attention towards the rapid pace at which AI is progressing. In the latest such example of an AI outsmarting human beings, a deep neural network model developed by Alibaba fared better than humans in a reading comprehension test.
If you asked most people, they'd probably say that computers and other gadgets are pretty good at communicating information to us, whether it's by providing directions to an important business meeting or finding the best recipe for gluten-free apple pie. And yet, computers still don't communicate with us nearly as intuitively as we communicate with each other. If you type a query into a search engine, for example, chances are you'll get a list of websites to click on. But if you ask a person a question, she'll respond with an answer, or perhaps ask another question to get more information before answering. Microsoft is hoping to improve how well computers can communicate information to us.
Machine comprehension of text is the problem to answer a query based on a given context. Many existing systems use RNN-based units for contextual modeling linked with some attention mechanisms. In this paper, however, we propose StackReader, an end-to-end neural network model, to solve this problem, without recurrent neural network (RNN) units and its variants. This simple model is based solely on attention mechanism and gated convolutional neural network. Experiments on SQuAD have shown to have relatively high accuracy with a significant decrease in training time.