We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency trees. We build a strong logistic regression model, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). However, human performance (86.8%) is much higher, indicating that the dataset presents a good challenge problem for future research. 
The dataset is freely available at this https URL

SQuAD: 100,000+ Questions for Machine Comprehension of Text

We present the Natural Questions corpus, a question answering data set. Questions consist of real anonymized, aggregated queries issued to the Google search engine. An annotator is presented with a...

/pdf/natural-questions-a-benchmark-for-question-answering-10mm1ytgmc.pdf

Natural Questions: A Benchmark for Question Answering Research

Generation of 3D data by deep neural network has been attracting increasing attention in the research community. The majority of extant works resort to regular representations such as volumetric grids or collection of images, however, these representations obscure the natural invariance of 3D shapes under geometric transformations, and also suffer from a number of other issues. In this paper we address the problem of 3D reconstruction from a single image, generating a straight-forward form of output &#x2013; point cloud coordinates. Along with this problem arises a unique and interesting issue, that the groundtruth shape for an input image may be ambiguous. Driven by this unorthordox output form and the inherent ambiguity in groundtruth, we design architecture, loss function and learning paradigm that are novel and effective. Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image. In experiments not only can our system outperform state-of-the-art methods on single image based 3D reconstruction benchmarks, but it also shows strong performance for 3D shape completion and promising ability in making multiple plausible predictions.

/pdf/a-point-set-generation-network-for-3d-object-reconstruction-2td63ffyqa.pdf

A Point Set Generation Network for 3D Object Reconstruction from a Single Image

We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node stores a pooled feature representation. This allows to focus memory allocation and computation to the relevant dense regions and enables deeper networks without compromising resolution. We demonstrate the utility of our OctNet representation by analyzing the impact of resolution on several 3D tasks including 3D object classification, orientation estimation and point cloud labeling.

https://openaccess.thecvf.com/content_cvpr_2017/papers/Riegler_OctNet_Learning_Deep_CVPR_2017_paper.pdf

OctNet: Learning Deep 3D Representations at High Resolutions

We present an approach to automatic 3D reconstruction of objects depicted in Web images. The approach reconstructs objects from single views. The key idea is to jointly analyze a collection of images of different objects along with a smaller collection of existing 3D models. The images are analyzed and reconstructed together. Joint analysis regularizes the formulated optimization problems, stabilizes correspondence estimation, and leads to reasonable reproduction of object appearance without traditional multi-view cues.

/pdf/single-view-reconstruction-via-joint-analysis-of-image-and-54zefdcsgj.pdf

Single-view reconstruction via joint analysis of image and shape collections

We have constructed a new "Who-did-What" dataset of over 200,000 fill-in-the-gap (cloze) multiple choice reading comprehension problems constructed from the LDC English Gigaword newswire corpus. The WDW dataset has a variety of novel features. First, in contrast with the CNN and Daily Mail datasets (Hermann et al., 2015) we avoid using article summaries for question formation. Instead, each problem is formed from two independent articles --- an article given as the passage to be read and a separate article on the same events used to form the question. Second, we avoid anonymization --- each choice is a person named entity. Third, the problems have been filtered to remove a fraction that are easily solved by simple baselines, while remaining 84% solvable by humans. We report performance benchmarks of standard systems and propose the WDW dataset as a challenge task for the community.

Who did What: A Large-Scale Person-Centered Cloze Dataset.

Taking advantage of the data gathering capability of wireless sensor networks (WSNs) as well as the data storage and processing ability of mobile cloud computing (MCC), WSN–MCC integration is attracting significant attention from both academia and industry. This paper focuses on processing of the sensory data in WSN–MCC integration, by identifying the critical issues concerning WSN–MCC integration and proposing a novel sensory data processing framework, which aims at transmitting desirable sensory data to the mobile users in a fast, reliable, and secure manner. The proposed framework could prolong the WSN lifetime, decrease the storage requirements of the sensors and the WSN gateway, and reduce the traffic load and bandwidth requirement of sensory data transmissions. In addition, the framework is capable of monitoring and predicting the future trend of the sensory data traffic, as well as improving its security. The framework further decreases the storage and processing overhead of the cloud, while enabling mobile users to securely obtain their desired sensory data faster. Analytical and experimental results are presented to demonstrate the effectiveness of the proposed framework.

A Novel Sensory Data Processing Framework to Integrate Sensor Networks With Mobile Cloud

We demonstrate significant improvement on the MCTest question answering task (Richardson et al., 2013) by augmenting baseline features with features based on syntax, frame semantics, coreference, and word embeddings, and combining them in a max-margin learning framework. We achieve the best results we are aware of on this dataset, outperforming concurrentlypublished results. These results demonstrate a significant performance gradient for the use of linguistic structure in machine comprehension.

/pdf/machine-comprehension-with-syntax-frames-and-semantics-jao0hw10wv.pdf

Machine Comprehension with Syntax, Frames, and Semantics

Deep learning has emerged as a versatile tool for a wide range of NLP tasks, due to its superior capacity in representation learning. But its applicability is limited by the reliance on annotated examples, which are difficult to produce at scale. Indirect supervision has emerged as a promising direction to address this bottleneck, either by introducing labeling functions to automatically generate noisy examples from unlabeled text, or by imposing constraints over interdependent label decisions. A plethora of methods have been proposed, each with respective strengths and limitations. Probabilistic logic offers a unifying language to represent indirect supervision, but end-to-end modeling with probabilistic logic is often infeasible due to intractable inference and learning. In this paper, we propose deep probabilistic logic (DPL) as a general framework for indirect supervision, by composing probabilistic logic with deep learning. DPL models label decisions as latent variables, represents prior knowledge on their relations using weighted first-order logical formulas, and alternates between learning a deep neural network for the end task and refining uncertain formula weights for indirect supervision, using variational EM. This framework subsumes prior indirect supervision methods as special cases, and enables novel combination via infusion of rich domain and linguistic knowledge. Experiments on biomedical machine reading demonstrate the promise of this approach.

/pdf/deep-probabilistic-logic-a-unifying-framework-for-indirect-460b4l5zuv.pdf

Hai Wang

Papers

Single-view reconstruction via joint analysis of image and shape collections

Who did What: A Large-Scale Person-Centered Cloze Dataset.

A Novel Sensory Data Processing Framework to Integrate Sensor Networks With Mobile Cloud

Machine Comprehension with Syntax, Frames, and Semantics

Deep Probabilistic Logic: A Unifying Framework for Indirect Supervision