Presented by:

Ken Kahn

from University of Oxford

Join the conversation for this session on the Snap! Forum - https://forum.snap.berkeley.edu/t/lightning-talks-using-hyperblocks-to-solve-word-analogy-problems/4818

Word embeddings use machine learning to turn words into lists of 300 numbers. By doing some addition and subtraction on these lists using Snap!'s hyperblocks one can solve word analogy problems in a surprisingly straightforward manner. E.g. man is to woman as father is to X.

I'll demonstrate this project that works in 15 different languages.

Duration:
5 min
Room:
Snap!Shot Zoom Room
Conference:
Snap!shot 2020
Difficulty:
Medium

Happening at the same time:

  1. Social Hall
  2. Start Time:
    2020 December 12 09:00

    Room:
    Social Room

There are no upcoming events.