Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation

In this paper, we consider the problem of machine reading task when the questions are in the form of keywords, rather than natural language. In recent years, researchers have achieved signi€cant success on machine reading comprehension tasks, such as S‹AD and TriviaQA. Œese datasets provide a natural language question sentence and a pre-selected passage, and the goal is to answer the question according to the passage. However, in the situation of interacting with machines by means of text, people are more likely to raise a query in form of several keywords rather than a complete sentence. Œe keyword-based query comprehension is a new challenge, because small variations to a question may completely change its semantical information, thus yield di‚erent answers. In this paper, we propose a novel neural network system that consists a Demand Optimization Model based on a passage-aŠention neural machine translation and a Reader Model that can €nd the answer given the optimized question. Œe Demand Optimization Model optimizes the original query and output multiple reconstructed questions, then the Reader Model takes the new questions as input and locate the answers from the passage. To make predictions robust, an evaluation mechanism will score the reconstructed questions so the €nal answer strike a good balance between the quality of both the Demand Optimization Model and the Reader Model. Experimental results on several datasets show that our framework signi€cantly improves multiple strong baselines on this challenging task.