Textbook Question Answering (TQA) is a task to choose the most proper answers by reading a multi-modal context of abundant essays and images. TQA serves as a favorable test bed for visual and textual reasoning. However, most of the current methods are incapable of reasoning over the long contexts and images. To address this issue, we propose a novel approach of Instructor Guidance with Memory Networks (IGMN) which conducts the TQA task by finding contradictions between the candidate answers and their corresponding context. We build the Contradiction Entity-Relationship Graph (CERG) to extend the passage-level multi-modal contradictions to an essay level. The machine thus performs as an instructor to extract the essay-level contradictions as the Guidance. Afterwards, we exploit the memory networks to capture the information in the Guidance, and use the attention mechanisms to jointly reason over the global features of the multi-modal input. Extensive experiments demonstrate that our method outperforms the state-of-the-arts on the TQA dataset. The source code is available at https://github.com/freerailway/igmn.

Textbook Question Answering (TQA) [1] is a newly proposed task to answer arbitrary questions in middle school curricula, which has particular challenges to understand the long essays in additional to the images. Bilinear models [2], [3] are effective at learning high-level associations between questions and images, but are inefficient to handle the long essays. In this paper, we propose an Essay-anchor Attentive Multi-modal Bilinear pooling (EAMB), a novel method to encode the long essays into the joint space of the questions and images. The essay-anchors, embedded from the keywords, represent the essay information in a latent space. We propose a novel network architecture to pay special attention on the keywords in the questions, consequently encoding the essay information into the question features, and thus the joint space with the images. We then use the bilinear models to extract the multi-modal interactions to obtain the answers. EAMB successfully utilizes the redundancy of the pre-trained word embedding space to represent the essay-anchors. This avoids the extra learning difficulties from exploiting large network structures. Quantitative and qualitative experiments show the outperforming effects of EAMB on the TQA dataset.

Deep Random Walk (DeepWalk) can learn a latent space representation for describing the topological structure of a network.However, for relational network classification, DeepWalk can be suboptimal as it lacks a mechanism to optimize the objective of the target task.In this paper, we present Discriminative Deep Random Walk (DDRW), a novel method for relational network classification.By solving a joint optimization problem, DDRW can learn the latent space representations that well capture the topological structure and meanwhile are discriminative for the network classification task.Our experimental results on several real social networks demonstrate that DDRW significantly outperforms DeepWalk on multilabel network classification tasks, while retaining the topological structure in the latent space.DDRW is stable and consistently outperforms the baseline methods by various percentages of labeled data.DDRW is also an online method that is scalable and can be naturally parallelized.

Mobile objects can be used to gather samples from a sensor field. Civilian vehicles or even human beings equipped with proper wireless communication devices can be used as mobile sinks that retrieve sensor-data from sampling points within a large sensor field. A key challenge is how to gather the sensor data in a manner that is energy efficient with respect to the sensor nodes that serve as sources of the sensor data. In this paper, an algorithmic technique called Band-based Directional Broadcast is introduced to control the direction of broadcasts that originate from sensor nodes. The goal is to direct each broadcast of sensor data toward the mobile sink, thus reducing costly forwarding of sensor data packets. The technique is studied by simulations that consider energy consumption and data deliverability.