We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The key hypothesis of multilingual learning is that by combining cues from multi...
Benjamin Snyder, Tahira Naseem, Jacob Eisenstein, ...
We report on three distinct experiments that provide new valuable insights into learning algorithms and datasets. We first describe two effective meta-features that significantly ...
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
Stimulus arrays are inevitably presented at different positions on the retina in visual tasks, even those that nominally require fixation. In particular, this applies to many perc...
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...