Session 6: Hands-on practice

Investigate the experimental models:

• Window size: 2
• Dimensions: 1,000
• Corpus size: 500,000 words
• Names removed in data preparation
• Minimal data preparation

Make a list: how many evidences of the text preparation and model training procesess can you find?

Discuss:

• What features of your own corpus might be manifesting in your model?
• What changes might you want to make for future research?
• Test your own model: can you find any evidence of these features in the model, as you did with the experimental ones?
• What would you need to explain about your choices in data preparation in any research based on your model?

Word Vectors: Hands-on Practice and Group Work, Intensive Research-focused slide 02 of 6

© 2019 Syd Bauman, Julia Flanders, Sarah Connell, and the Women Writers Project This TEI-encoded XML file is available under the terms of the Creative Commons Attribution-ShareAlike 3.0 (Unported) license.