Text World and Word Embedding Lower Bounds

Data Skeptic

Episode | Podcast

Date: Fri, 08 Feb 2019 16:00:00 +0000

<p class="p1"><span class="s1">In the first half of this episode, Kyle speaks with Marc-Alexandre Côté and Wendy Tay about Text World.<span class="Apple-converted-space"> </span> Text World is an engine that simulates text adventure games.<span class="Apple-converted-space"> </span> Developers are encouraged to try out their reinforcement learning skills building agents that can programmatically interact with the generated text adventure games.</span></p> <p class="p2"> </p> <p class="p1"><span class="s1">In the second half of this episode, Kyle interviews Kevin Patel about his paper Towards Lower Bounds on Number of Dimensions for Word Embeddings.<span class="Apple-converted-space"> </span> In this research, the explore an important question of how many hidden nodes to use when creating a word embedding.</span></p>