Outline extraction has been widely applied in online consultation to help experts quickly understand individual cases. Given a specific case described as unstructured plain text, outline extraction aims to make a summary for this case by answering a set of questions, which in fact is a new type of machine reading comprehension task. Inspired by a recently popular memory network, we propose a novel question-specific memory cell network (QSMCN) to extract information related to multiple questions on-the-fly as it reads texts. QSMCN constructs a specific memory cell for each question, which is sequentially expanded in recurrent neural network style. Each cell contains three specific vectors to first identify whether current input is related to corresponding question and then update question-specific case representation. We add a penalization term in the loss function to make extracted knowledge more reasonable and interpretable. To support this study, we construct a new outline extraction corpus, InjuryCase, 1 which is composed of 3,995 real Chinese occupational injury cases. Experimental results show that our method makes a significant improvement. We further apply the proposed framework on two multi-aspect extraction tasks and find that the proposed model also remarkably outperforms existing state-of-the-art methods of the aspect extraction task.

We propose Object-oriented Neural Programming (OONP), a framework for semantically parsing documents in specific domains.Basically, OONP reads a document and parses it into a predesigned object-oriented data structure that reflects the domain-specific semantics of the document.An OONP parser models semantic parsing as a decision process: a neural netbased Reader sequentially goes through the document, and builds and updates an intermediate ontology during the process to summarize its partial understanding of the text.OONP supports a big variety of forms (both symbolic and differentiable) for representing the state and the document, and a rich family of operations to compose the representation.An OONP parser can be trained with supervision of different forms and strength, including supervised learning (SL) , reinforcement learning (RL) and hybrid of the two.Our experiments on both synthetic and real-world document parsing tasks have shown that OONP can learn to handle fairly complicated ontology with training data of modest sizes.* The work was done when these authors worked as interns at DeeplyCurious.ai.

In early years, text classification is typically accomplished by feature-based classifiers; recently, neural networks, as powerful classifiers, make it possible to work with raw input as the text stands. In this paper, we propose a novel framework, Jumper, inspired by the cognitive process of text reading, that models text classification as a sequential decision process. Basically, Jumper is a neural system that can scan a piece of text sequentially and make classification decision at the time it chooses. Both the classification and when to make the classification are part of the decision process which are controlled by the policy net and trained with reinforcement learning to maximize the overall classification accuracy. Experimental results show that a properly trained Jumper has the following properties: (1) It can make decisions whenever the evidence is enough, therefore reducing the total text reading by 30~40% and often finding the key rationale of prediction. (2) It can achieve classification accuracy better or comparable to state-of-the-art model in several benchmark and industrial datasets.

Although brushless DC motor (BLDCM) is widely used, testing its drives is troublesome. To deal with the problem, the power hardware-in-the-loop (PHIL) simulator is necessary to replace the real BLDCM, which can exchange not only signals but also electric power with the drive. However, few literatures discussed the PHIL simulator for BLDCM applications. Design method for the BLDCM PHIL simulator is proposed in this paper. The line voltage based BLDCM transient model is established, which can improve the fidelity during commutation and predict the floating phase voltage. The derivation of BLDCM numerical model is based on the bilinear transform and inverse Z-transform, which can achieve higher accuracy and cost low computational effort. Moreover, without power bus connection between the drive and PHIL simulator, the overall structure of PHIL simulator is constructed based on line voltage and only one digital signal processor (DSP). In addition, the analog frond end (AFE) for measuring the high speed PWM line voltage from the drive and the linear mode power stage are also designed. The effectiveness of the proposed method is validated by experimental results.