In this paper, we introduce the Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects. First, a reattention mechanism is proposed to refine current attentions by directly accessing to past attentions that are temporally memorized in a multi-round alignment architecture, so as to avoid the problems of attention redundancy and attention deficiency. Second, a new optimization approach, called dynamic-critical reinforcement learning, is introduced to extend the standard supervised method. It always encourages to predict a more acceptable answer so as to address the convergence suppression problem occurred in traditional reinforcement learning algorithms. Extensive experiments on the Stanford Question Answering Dataset (SQuAD) show that our model achieves state-of-the-art results. Meanwhile, our model outperforms previous systems by over 6% in terms of both Exact Match and F1 metrics on two adversarial SQuAD datasets.

Detecting misbehavior (such as transmissions of false information) in vehicular ad hoc networks (VANETs) is very important problem with wide range of implications including safety related and congestion avoidance applications. We discuss several limitations of existing misbehavior detection schemes (MDS) designed for VANETs. Most MDS are concerned with detection of malicious nodes. In most situations, vehicles would send wrong information because of selfish reasons of their owners, e.g. for gaining access to a particular lane. Because of this (rational behavior), it is more important to detect false information than to identify misbehaving nodes. We introduce the concept of datacentric misbehavior detection and propose algorithms which detect false alert messages and misbehaving nodes by observing their actions after sending out the alert messages. With the datacentric MDS, each node can independently decide whether an information received is correct or false. The decision is based on the consistency of recent messages and new alert with reported and estimated vehicle positions. No voting or majority decisions is needed, making our MDS resilient to Sybil attacks. Instead of revoking all the secret credentials of misbehaving nodes, as done in most schemes, we impose fines on misbehaving nodes (administered by the certification authority), discouraging them to act selfishly. This reduces the computation and communication costs involved in revoking all the secret credentials of misbehaving nodes.

Open-domain targeted sentiment analysis aims to detect opinion targets along with their sentiment polarities from a sentence. Prior work typically formulates this task as a sequence tagging problem. However, such formulation suffers from problems such as huge search space and sentiment inconsistency. To address these problems, we propose a span-based extract-then-classify framework, where multiple opinion targets are directly extracted from the sentence under the supervision of target span boundaries, and corresponding polarities are then classified using their span representations. We further investigate three approaches under this framework, namely the pipeline, joint, and collapsed models. Experiments on three benchmark datasets show that our approach consistently outperforms the sequence tagging baseline. Moreover, we find that the pipeline model achieves the best performance compared with the other two models.

Machine reading comprehension with unanswerable questions aims to abstain from answering when no answer can be inferred. In addition to extract answers, previous works usually predict an additional "no-answer" probability to detect unanswerable cases. However, they fail to validate the answerability of the question by verifying the legitimacy of the predicted answer. To address this problem, we propose a novel read-then-verify system, which not only utilizes a neural reader to extract candidate answers and produce noanswer probabilities, but also leverages an answer verifier to decide whether the predicted answer is entailed by the input snippets. Moreover, we introduce two auxiliary losses to help the reader better handle answer extraction as well as noanswer detection, and investigate three different architectures for the answer verifier. Our experiments on the SQuAD 2.0 dataset show that our system obtains a score of 74.2 F1 on test set, achieving state-of-the-art results at the time of submission (Aug. 28th, 2018).

To date, high-performance organic electrochemical transistors (OECTs) are mostly based on polythiophene systems. Donor-acceptor (D-A) conjugated polymers are expected to be promising materials for OECTs owing to their high mobility...