Papers

Learn more about AI2's Lasting Impact Award
Viewing 921-930 of 1025 papers
  • LCNN: Lookup-based Convolutional Neural Network

    Hessam Bagherinezhad, Mohammad Rastegari, and Ali FarhadiCVPR2017 Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables efficient learning and…
  • Learning to Predict Citation-Based Impact Measures

    Luca Weihs and Oren EtzioniJCDL2017 Citations implicitly encode a community's judgment of a paper's importance and thus provide a unique signal by which to study scientific impact. Efforts in understanding and refining this signal are reflected in the probabilistic modeling of citation networks…
  • Learning What is Essential in Questions

    Daniel Khashabi, Tushar Khot, Ashish Sabharwal, and Dan RothCoNLL2017 Question answering (QA) systems are easily distracted by irrelevant or redundant words in questions, especially when faced with long or multi-sentence questions in difficult domains. This paper introduces and studies the notion of essential question terms…
  • Leveraging Term Banks for Answering Complex Questions: A Case for Sparse Vectors

    Peter D. TurneyarXiv2017 While open-domain question answering (QA) systems have proven effective for answering simple questions, they struggle with more complex questions. Our goal is to answer more complex questions reliably, without incurring a significant cost in knowledge…
  • Neural Semantic Parsing with Type Constraints for Semi-Structured Tables

    Jayant Krishnamurthy, Pradeep Dasigi, and Matt GardnerEMNLP2017 We present a new semantic parsing model for answering compositional questions on semi-structured Wikipedia tables. Our parser is an encoder-decoder neural network with two key technical innovations: (1) a grammar for the decoder that only generates well-typed…
  • Ontology Aware Token Embeddings for Prepositional Phrase Attachment

    Pradeep Dasigi, Waleed Ammar, Chris Dyer, and Eduard HovyACL2017 Type-level word embeddings use the same set of parameters to represent all instances of a word regardless of its context, ignoring the inherent lexical ambiguity in language. Instead, we embed semantic concepts (or synsets) as defined in WordNet and represent…
  • Pros and Cons of Autonomous Weapons Systems

    Amitai Etzioni and Oren EtzioniMilitary Review2017 Autonomous weapons systems and military robots are progressing from science fiction movies to designers' drawing boards, to engineering laboratories, and to the battlefield. These machines have prompted a debate among military planners, roboticists, and…
  • QSAnglyzer: Visual Analytics for Prismatic Analysis of Question Answering System Evaluations

    Nan-Chen Chen and Been KimVAST2017 Developing sophisticated artificial intelligence (AI) systems requires AI researchers to experiment with different designs and analyze results from evaluations (we refer this task as evaluation analysis). In this paper, we tackle the challenges of evaluation…
  • Query-Reduction Networks for Question Answering

    Minjoon Seo, Sewon Min, Ali Farhadi, Hannaneh HajishirziICLR2017 In this paper, we study the problem of question answering when reasoning over multiple facts is required. We propose Query-Reduction Network (QRN), a variant of Recurrent Neural Network (RNN) that effectively handles both short-term (local) and long-term…
  • See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content

    Roozbeh Mottaghi, Connor Schenck, Dieter Fox, Ali FarhadiICCV2017 Humans have rich understanding of liquid containers and their contents; for example, we can effortlessly pour water from a pitcher to a cup. Doing so requires estimating the volume of the cup, approximating the amount of water in the pitcher, and predicting…