Daniel Khashabi

Allen Institute for AI
http://danielkhashabi.com
Publications64
h-index18
Citations1,119
Highly Influential Citations159
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • D. Roth
  • 524 Publications • 23,234 Citations
  • Ashish Sabharwal
  • 149 Publications • 4,116 Citations
  • P. Clark
  • 256 Publications • 3,420 Citations
  • Tushar Khot
  • 77 Publications • 1,523 Citations
  • Publications
  • Influence
Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences
TLDR
We present a reading comprehension challenge in which questions can only be answered by taking into account information from multiple sentences, and demonstrate the difficulty of this challenge, despite a high human performance. Expand
UnifiedQA: Crossing Format Boundaries With a Single QA System
TLDR
We use the latest advances in language modeling to build a single pre-trained QA model, UNIFIEDQA, that performs well across 19 QA datasets spanning 4 diverse formats. Expand
Solving Hard Coreference Problems
TLDR
In this paper we propose an algorithmic solution that involves a new representation for the knowledge required to address hard coreference problems, along with a constrained optimization framework that uses this knowledge in coreference decision making. Expand
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
TLDR
We propose an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semi-automatically constructed knowledge base, to achieve substantially improved results. Expand
Joint Demosaicing and Denoising via Learned Nonparametric Random Fields
TLDR
We introduce a machine learning approach to demosaicing, the reconstruction of color images from incomplete color filter array samples by learning a statistical model of images and noise from hundreds of natural images. Expand
Online Learning with Adversarial Delays
TLDR
We show that online-gradient-descent [1] and follow-the-perturbed-leader achieve regret O(√D) in the delayed setting, where D is the sum of delays of each round's feedback. Expand
Question Answering via Integer Programming over Semi-Structured Knowledge
TLDR
We propose a structured inference system for this task, formulated as an Integer Linear Program (ILP), that answers natural language questions using a semi-structured knowledge base derived from text, including questions requiring multi-step inference and a combination of multiple facts. Expand
"Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understanding
TLDR
We define five classes of temporal commonsense, and use crowdsourcing to develop a new dataset, MCTACO, that serves as a test set for this task. Expand
Question Answering as Global Reasoning Over Semantic Abstractions
TLDR
We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. Expand
Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims
TLDR
We propose the task of substantiated perspective discovery where, given a claim, a system is expected to discover a diverse set of well-corroborated perspectives that take a stance with respect to the claim. Expand
...
1
2
3
4
5
...