Automatic short answer grading (ASAG), which autonomously score student answers according to reference answers, provides a cost-effective and consistent approach to teaching professionals and can reduce their monotonous and tedious grading workloads. However, ASAG is a very challenging task due to two reasons: (1) student answers are made up of free text which requires a deep semantic understanding; and (2) the questions are usually open-ended and across many domains in K-12 scenarios. In this paper, we propose a generalized end-to-end ASAG learning framework which aims to (1) autonomously extract linguistic information from both student and reference answers; and (2) accurately model the semantic relations between free-text student and reference answers in open-ended domain. The proposed ASAG model is evaluated on a large real-world K-12 dataset and can outperform the state-of-the-art baselines in terms of various evaluation metrics. 1 Introduction Assessing the knowledge acquired by students is one of the most important aspects of the learning process as it provides feedback to help students correct their misunderstanding of knowledge and improves their overall learning performance. Traditionally, the assessing paradigm is often conducted by instructors or teachers. However, this access paradigm is not suitable in many cases especially when teaching resources are not readily available.

A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and unstructured data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and unstructured data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks.

Noname manuscript No. (will be inserted by the editor)Active Collaboration in Relative Observation for Multi-agent Visual SLAM based on Deep Q Network Zhaoyi Pei · Piaosong Hao · Meixiang Quan · Muhammad Zuhair Qadir · Guo Li Received: date / Accepted: date Abstract This paper proposes a unique active relative localization mechanism for multi-agent Simultaneous Localization and Mapping(SLAM),in which a agent to be observed are considered as a task, which is performed by others assisting that agent by relative observation. A task allocation algorithm based on deep reinforcement learning are proposed for this mechanism. Each agent can choose whether to localize other agents or to continue independent SLAM on it own initiative. By this way, the process of each agent SLAM will be interacted by the collaboration. Firstly, based on the characteristics of ORBSLAM, a unique observation function which models the whole MAS is obtained. Secondly, a novel type of Deep Q network(DQN) called MAS-DQN is deployed to learn correspondence between Q Value and state-action pair, abstract representation of agents in MAS are learned in the process of collaboration amongZhaoyi Pei Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China Email: peizhaoyi@stu.hit.edu.cn Songhao Piao Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China Email: piaosh@hit.edu.cn Meixiang Quan Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China Email: 15b903042@hit.edu.cn

In recent years, there has been increased research interest in detecting anomalies in temporal streaming data. A variety of algorithms have been developed in the data mining community, which can be divided into two categories (i.e., general and ad hoc). In most cases, general approaches assume the one-size-fits-all solution model where a single anomaly detector can detect all anomalies in any domain. To date, there exists no single general method that has been shown to outperform the others across different anomaly types, use cases and datasets. On the other hand, ad hoc approaches that are designed for a specific application lack flexibility. Adapting an existing algorithm is not straightforward if the specific constraints or requirements for the existing task change. In this paper, we propose SAFARI, a general framework formulated by abstracting and unifying the fundamental tasks in streaming anomaly detection, which provides a flexible and extensible anomaly detection procedure. SAFARI helps to facilitate more elaborate algorithm comparisons by allowing us to isolate the effects of shared and unique characteristics of different algorithms on detection performance. Using SAFARI, we have implemented various anomaly detectors and identified a research gap that motivates us to propose a novel learning strategy in this work. We conducted an extensive evaluation study of 20 detectors that are composed using SAFARI and compared their performances using real-world benchmark datasets with different properties. The results indicate that there is no single superior detector that works well for every case, proving our hypothesis that "there is no free lunch" in the streaming anomaly detection world. Finally, we discuss the benefits and drawbacks of each method in-depth and draw a set of conclusions to guide future users of SAFARI.

Neural dialogue models have been widely adopted in various chatbot applications because of their good performance in simulating and generalizing human conversations. However, there exists a dark side of these models -- due to the vulnerability of neural networks, a neural dialogue model can be manipulated by users to say what they want, which brings in concerns about the security of practical chatbot services. In this work, we investigate whether we can craft inputs that lead a well-trained black-box neural dialogue model to generate targeted outputs. We formulate this as a reinforcement learning (RL) problem and train a Reverse Dialogue Generator which efficiently finds such inputs for targeted outputs. Experiments conducted on a representative neural dialogue model show that our proposed model is able to discover such desired inputs in a considerable portion of cases. Overall, our work reveals this weakness of neural dialogue models and may prompt further researches of developing corresponding solutions to avoid it.

We focus on the following natural question: is it possible to influence the outcome of a voting process through the strategic provision of information to voters who update their beliefs rationally? We investigate whether it is computationally tractable to design a signaling scheme maximizing the probability with which the sender's preferred candidate is elected. We focus on the model recently introduced by Arieli and Babichenko (2019) (i.e., without inter-agent externalities), and consider, as explanatory examples, $k$-voting rule and plurality voting. There is a sharp contrast between the case in which private signals are allowed and the more restrictive setting in which only public signals are allowed. In the former, we show that an optimal signaling scheme can be computed efficiently both under a $k$-voting rule and plurality voting. In establishing these results, we provide two general (i.e., applicable to settings beyond voting) contributions. Specifically, we extend a well known result by Dughmi and Xu (2017) to more general settings, and prove that, when the sender's utility function is anonymous, computing an optimal signaling scheme is fixed parameter tractable w.r.t. the number of receivers' actions. In the public signaling case, we show that the sender's optimal expected return cannot be approximated to within any factor under a $k$-voting rule. This negative result easily extends to plurality voting and problems where utility functions are anonymous.

Erecting a new building ranks among the most inefficient, polluting activities humans undertake. The construction sector is responsible for nearly 40% of the world's total energy consumption and CO2 emissions, according to a UN global survey (pdf). A consortium of Swiss researchers has one answer to the problem: working with robots. The proof of concept comes in the form of the DFAB House, celebrated as the first habitable building designed and planned using a choreography of digital fabrication methods. The three-level building near Zurich features 3D-printed ceilings, energy-efficient walls, timber beams assembled by robots on site, and an intelligent home system.

This past May I worked with the Internet Archive's Television News Archive to apply Google's suite of cloud AI APIs to analyze a week of television news coverage to examine how AI "sees" television and what insights we might gain into the world of non-consumptive deep learning-powered video understanding. Using Google's video, image, speech and natural language APIs as lenses, more than 600GB of machine annotations trace how deep learning algorithms today understand video. What lessons can we learn about the state of AI today and how it can be applied in creative ways to catalog and explore the vast world of video? Working with the Internet Archive's Television News Archive, a week of television news was selected covering CNN, MSNBC and Fox News and the morning and evening broadcasts of San Francisco affiliates KGO (ABC), KPIX (CBS), KNTV (NBC) and KQED (PBS) from April 15 to April 22, 2019, totaling 812 hours of television news. This week was selected due to it having two major stories, one national (the Mueller report release on April 18th) and one international (the Notre Dame fire on April 15th).

Facebook is working on developing an AI voice assistant similar in functionality to Amazon Alexa, Google Assistant, or Siri, according to a report from CNBC and a later statement from a Facebook representative. The CNBC report, which cites "several people familiar with the matter," says the project has been ongoing since early 2018 in the company's offices in Redmond, Washington. The endeavor is led by Ira Snyder, whose listed title on LinkedIn is "Director, AR/VR and Facebook Assistant at Facebook." Facebook Assistant may be the name of the project. CNBC writes that Facebook has been reaching out to vendors in the smart-speaker supply chain, suggesting that Portal may only be the first of many smart devices the company makes. When contacted for comment, Facebook sent a statement to Reuters, The Verge, and others, saying: "We are working to develop voice and AI assistant technologies that may work across our family of AR/VR products including Portal, Oculus, and future products."

Because of its mind boggling, information driven applications, for example, voice and picture acknowledgment, AI has been picking up prevalence. Computer based intelligence offers a noteworthy venture opportunity, as it very well may be utilized over different innovations, to defeat the difficulties relating to high registering force, high information volumes, and enhancement of information stockpiling. Associations are putting to join AI capacities into their item portfolio, in the aeronautics business. Calculations help to foresee delays, in this manner offering air terminals and carriers a superior shot at maintaining a strategic distance from postponements. Carriers, for example, Emirates and easyJet Airline Company Limited, are utilizing the innovation, to acquire an effortless ticketing procedure and offer a customized, upbeat in-flight understanding.