Attending to Long-Distance Document Context for Sequence Labeling

1 code implementation • Findings of the Association for Computational Linguistics 2020 • Matthew J{\"o}rke, Jon Gillick, Matthew Sims, David Bamman

We present in this work a method for incorporating global context in long documents when making local decisions in sequence labeling problems like NER.

NER

Breaking Speech Recognizers to Imagine Lyrics

1 code implementation • 15 Dec 2019 • Jon Gillick, David Bamman

We introduce a new method for generating text, and in particular song lyrics, based on the speech-like acoustic qualities of a given audio file.

Learning to Groove with Inverse Sequence Transformations

1 code implementation • 14 May 2019 • Jon Gillick, Adam Roberts, Jesse Engel, Douglas Eck, David Bamman

We explore models for translating abstract musical ideas (scores, rhythms) into expressive performances using Seq2Seq and recurrent Variational Information Bottleneck (VIB) models.

Generative Adversarial Network Quantization

Please Clap: Modeling Applause in Campaign Speeches

no code implementations • NAACL 2018 • Jon Gillick, David Bamman

This work examines the rhetorical techniques that speakers employ during political campaigns.

Telling Stories with Soundtracks: An Empirical Analysis of Music in Film

no code implementations • WS 2018 • Jon Gillick, David Bamman

Soundtracks play an important role in carrying the story of a film.

Image Captioning Question Answering