• Publications
  • Influence
CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense
TLDR
We introduce the CODAH dataset, an adversarially-constructed evaluation dataset for testing commonsense knowledge using sentence-completion questions that describe situations observed in video. Expand
  • 18
  • 3
  • PDF
Multi-sense Definition Modeling using Word Sense Decompositions
TLDR
We introduce a new method that enables definition modeling for multiple senses of the same word from a mixed-sense embedding. Expand
  • 4
  • 1
  • PDF
Model selection for deep audio source separation via clustering analysis
TLDR
We present a confidence measure that does not require ground truth to estimate separation quality, given a deep model and audio mixture. Expand
  • 1
  • PDF
Bach or Mock? A Grading Function for Chorales in the Style of J.S. Bach
TLDR
Deep generative systems that learn probabilistic models from a corpus of existing music do not explicitly encode knowledge of a musical style, compared to traditional rule-based systems. Expand
  • 1
  • PDF
Comparison of Discourse Surrounding CRISPR/Cas9 in the Media and Peer-Re- viewed Literature
Cas9, a gene-editing technique that has had a profound impact on the field of genetic research in recent years. Compared to its alternatives, such as TALENs (Transcription Activator-Like Nucleases)Expand
Incorporating Music Knowledge in Continual Dataset Augmentation for Music Generation
TLDR
We present augmentative generation (Aug-Gen), a method of dataset augmentation for any music generation system trained on a resource-constrained domain. Expand