activity
20152021
most citedNon-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields

26 citations · 33 across the 4 of their papers we have counts for

collaborators

5 papers

cs.IR20216 cited

Podcast Metadata and Content: Episode Relevance andAttractiveness in Ad Hoc Search

Ben Carterette, Rosie Jones, Gareth F. Jones +6

Rapidly growing online podcast archives contain diverse content on a wide range of topics. These archives form an important resource for entertainment and professional use, but the…

cs.IR20211 cited

Current Challenges and Future Directions in Podcast Information Access

Rosie Jones, Hamed Zamani, Markus Schedl +11

Podcasts are spoken documents across a wide-range of genres and styles, with growing listenership across the world, and a rapidly lowering barrier to entry for both listeners and c…

cs.CL2021

Spotify at TREC 2020: Genre-Aware Abstractive Podcast Summarization

Rezvaneh Rezapour, Sravana Reddy, Ann Clifton +1

This paper contains the description of our submissions to the summarization task of the Podcast Track in TREC (the Text REtrieval Conference) 2020. The goal of this challenge was t…

cs.CL2020

The Spotify Podcast Dataset

Ann Clifton, Aasish Pappu, Sravana Reddy +4

Podcasts are a relatively new form of audio media. Episodes appear on a regular cadence, and come in many different formats and levels of formality. They can be formal news journal…

stat.ML201526 cited

Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields

Mark Schmidt, Reza Babanezhad, Mohamed Osama Ahmed +3

We apply stochastic average gradient (SAG) algorithms for training conditional random fields (CRFs). We describe a practical implementation that uses structure in the CRF gradient…