• Publications
  • Influence
Learning to rank using gradient descent
TLDR
We investigate using gradient descent methods for learning ranking functions; we propose a simple probabilistic cost function; we introduce RankNet, an implementation of these ideas using a neural network to model the underlying ranking function. Expand
  • 2,127
  • 258
  • PDF
MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text
TLDR
We present MCTest, a freely available set of stories and associated questions intended for research on the machine comprehension of text. Expand
  • 457
  • 84
  • PDF
Full body gait analysis with Kinect
TLDR
We present an accurate gait analysis system that is economical and non-intrusive and can be used for continuous gait tracking at home. Expand
  • 280
  • 10
  • PDF
Automatic Discovery of Personal Topics to Organize Email
TLDR
We present in this paper a procedure to automatically discover a user s personal topics by clustering their emails. Expand
  • 32
  • 3
  • PDF
A foreground-background separation algorithm for image compression
TLDR
We develop the SLIm system for separating text and line drawing from background images, in order to compress both more effectively is proposed. Expand
  • 20
  • 2
  • PDF
Animacy Detection with Voting Models
TLDR
Animacy detection is a problem whose solution has been shown to be beneficial for a number of syntactic and semantic tasks, such as anaphora and coreference resolution (Orǎsan and Evans, 2007). Expand
  • 7
  • 2
  • PDF
Using audio fingerprinting for duplicate detection and thumbnail generation
TLDR
This paper presents two new applications of audio fingerprinting, whose goal is to identify duplicate audio clips in a set, even if they differ in compression quality or duration, and thumbnail generation, which aims to provide a representative short clip of a music track. Expand
  • 35
  • PDF
Duplicate Detection and Audio Thumbnails with Audio Fingerprinting
TLDR
This paper presents two new applications: duplicate detection, whose goal is to identify duplicate audio clips in a set, even if they differ in compression quality or duration, and thumbnail generation, which aims at providing a representative short clip of a music track. Expand
  • 5
  • PDF
Selective Classifiers for Part-of-Speech Tagging
TLDR
We investigate the use of selective classifiers for part-of-speech tagging (POS). Expand
  • 1
  • PDF
Human Gait Identification using Depth Gradient Histogram Energy Image
Earlier work where we evaluated how traditional Gait Energy Image (GEI) can be used to identify human gait and eventually human ID. However, we also witnessed how inaccurate segmentation (due toExpand