Z2H Video 2, exercise E01 [Post #16, Day 33]
February 7, 2025•133 words
I have worked my way through building and "training" my trigram language model using the counting method.
Here are some fun names output from my model (I searched through the data set of names and some of these like Samiyah, Kaley, Aviyah, and Glen are actually in the data set, hmmm, is that a problem?):
- Ce
- Bra
- Jalius
- Rochityharlonimittain
- Luwak
- Ka
- Da
- Samiyah
- Javer
- Gotai
- Moriellavoji
- Preda
- Kaley
- Maside
- En
- Aviyah
- Folspihiliven
- Tahlas
- Kashruban
- Glen
Qualitatively speaking, they seem a little better than the names produced from the bigram language model. So naturally, the next step now is to evaluate the loss and determine if it performed better than the bigram language model.