Papers

Learn more about AI2's Lasting Impact Award
Viewing 811-820 of 988 papers
  • Understanding Convolutional Neural Networks for Text Classification

    Alon Jacovi, Oren Sar Shalom, Yoav GoldbergEMNLP • Workshop: Analyzing and interpreting neural networks for NLP2018 We present an analysis into the inner workings of Convolutional Neural Networks (CNNs) for processing text. CNNs used for computer vision can be interpreted by projecting filters into image space, but for discrete sequence inputs CNNs remain a mystery. We aim…
  • Word Sense Induction with Neural biLM and Symmetric Patterns

    Asaf Amrami, Yoav GoldbergEMNLP2018 An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors. We replace the ngram-based language model (LM) with a recurrent…
  • QuAC: Question Answering in Context

    Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang and Luke ZettlemoyerEMNLP2018 We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who poses a sequence of freeform questions to learn as much as…
  • Adaptive Stratified Sampling for Precision-Recall Estimation

    Ashish Sabharwal, Yexiang XueUAI2018 We propose a new algorithm for computing a constant-factor approximation of precision-recall (PR) curves for massive noisy datasets produced by generative models. Assessing validity of items in such datasets requires human annotation, which is costly and must…
  • Citation Count Analysis for Papers with Preprints

    Sergey Feldman, Kyle Lo, Waleed AmmarArXiv2018 We explore the degree to which papers prepublished on arXiv garner more citations, in an attempt to paint a sharper picture of fairness issues related to prepublishing. A paper’s citation count is estimated using a negative-binomial generalized linear model…
  • Construction of the Literature Graph in Semantic Scholar

    Waleed Ammar, Dirk Groeneveld, Chandra Bhagavatula, Iz Beltagy, Miles Crawford, Doug Downey, Jason Dunkelberger, Ahmed Elgohary, Sergey Feldman, Vu Ha, Rodney Kinney, Sebastian Kohlmeier, Kyle Lo, Tyler Murray, Hsu-Han Ooi, Matthew E. Peters, et al.NAACL-HLT2018 We describe a deployed scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery. The resulting literature graph consists of more than 280M nodes, representing papers…
  • Actor and Observer: Joint Modeling of First and Third-Person Videos

    Gunnar Sigurdsson, Cordelia Schmid, Ali Farhadi, Abhinav Gupta, Karteek AlahariCVPR2018 Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and seamlessly transfer knowledge between third-person (observer) and first-person…
  • Adversarial Training for Textual Entailment with Knowledge-Guided Examples

    Tushar Khot, Ashish Sabharwal and Dongyeop KangACL2018 We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for incorporating large…
  • AllenNLP: A Deep Semantic Natural Language Processing Platform

    Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson Liu, Matthew Peters, Michael Schmitz, Luke ZettlemoyerACL • NLP OSS Workshop2018 This paper describes AllenNLP, a platform for research on deep learning methods in natural language understanding. AllenNLP is designed to support researchers who want to build novel language understanding models quickly and easily. It is built on top of…
  • Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

    Aishwarya Agrawal, Dhruv Batra, Devi Parikh, Aniruddha KembhaviCVPR2018 A number of studies have found that today’s Visual Question Answering (VQA) models are heavily driven by superficial correlations in the training data and lack sufficient image grounding. To encourage development of models geared towards the latter, we…