Factors that affect the behavior of the model

Size of the corpus:

• a larger corpus supports more precise word positionings for uncommon words

Content of the corpus:

• genre?
• uniformity of language?

Preparation of the corpus:

• correction of errors (e.g. from OCR)
• elimination of noise

The training process:

• parameters!! (coming up soon)

Word Vectors Institute: Introductions and Overview slide 10 of 12

© 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.