Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 981-990 of 1033 papers
What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams
Peter Jansen, Niranjan Balasubramanian, Mihai Surdeanu, and Peter ClarkCOLING • 2016 QA systems have been making steady advances in the challenging elementary science exam domain. In this work, we develop an explanation-based analysis of knowledge and inference requirements, which supports a fine-grained characterization of the challenges. In…XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali FarhadiECCV • 2016 We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both the…You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali FarhadiCVPR • 2016 We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class…AI assisted ethics
Amitai Etzioni and Oren EtzioniEthics • 2016 The growing number of 'smart' instruments, those equipped with AI, has raised concerns because these instruments make autonomous decisions; that is, they act beyond the guidelines provided them by programmers. Hence, the question the makers and users of smart…Neural AMR: Sequence-to-Sequence Models for Parsing and Generation
Ioannis Konstas, Srini Iyer, Mark Yatskar, Yejin Choi, Luke ZettlemoyerACL • 2016 Sequence-to-sequence models have shown strong performance across a broad range of applications. However, their application to parsing and generating text using Abstract Meaning Representation (AMR) has been limited, due to the relatively limited amount of…My Computer is an Honor Student — but how Intelligent is it? Standardized Tests as a Measure of AI
Peter Clark and Oren EtzioniAI Magazine • 2016 Given the well-known limitations of the Turing Test, there is a need for objective tests to both focus attention on, and measure progress towards, the goals of AI. In this paper we argue that machine performance on standardized tests should be a key component…Closing the Gap Between Short and Long XORs for Model Counting
Shengjia Zhao, Sorathan Chaturapruek, Ashish Sabharwal, and Stefano ErmonAAAI • 2016 Many recent algorithms for approximate model counting are based on a reduction to combinatorial searches over random subsets of the space defined by parity or XOR constraints. Long parity constraints (involving many variables) provide strong theoretical…Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
Peter Clark, Oren Etzioni, Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Oyvind Tafjord, and Peter TurneyAAAI • 2016 What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test questions, but did not improve upon…Exact Sampling with Integer Linear Programs and Random Perturbations
Carolyn Kim, Ashish Sabharwal, and Stefano ErmonAAAI • 2016 We consider the problem of sampling from a discrete probability distribution specified by a graphical model. Exact samples can, in principle, be obtained by computing the mode of the original model perturbed with an exponentially many i.i.d. random variables…Hierarchical Semi-supervised Classification with Incomplete Class Hierarchies
Bhavana Dalvi, Aditya Mishra, and William W. CohenWSDM • 2016 In an entity classification task, topic or concept hierarchies are often incomplete. Previous work by Dalvi et al. has shown that in non-hierarchical semi-supervised classification tasks, the presence of such unanticipated classes can cause semantic drift for…