- What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).
I am working on the interaction between user and our app. I have prepared scripts that our app would read out when needed.
I have sent my code of spacy, which would identify DATE and PRICE to my team and they would connect that part with our web application. Additionally, I am working on the ITEM label this week. Since many things (apple, bed, laptop, etc.) would be assigned an ITEM label, it is not easy for spacy to learn which word would be recognized as ITEM. Therefore, our current trained spacy model does not perform ideally. I would add more training data to see what happen next week.
- Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?
on schedule
- What deliverables do you hope to complete in the next week?
- work with spacy
- prepare for performance test.
- This Week’s Special (Verification)
- Test parsing accuracy for ACTIONS (done)
I test this part with about 50 different text commands including different action verbs that maybe included in our system. The accuracy for this part is about 98% where “view” is considered as a noun instead of a verb. This will be fixed when I trained the model again later. The action verbs are pretty important because they will decided which webpage our app would show.
- Test parsing accuracy for DATE (done)
Since we will always require a time range (from xx month xx year to xx month xx year) in this part. I generated random pairs of month (12 different months) and year (from 2020 to 2040). And our app could ensure 100% accuracy. The DATE information is very important when the user want to view entries or generate report.
- Test parsing accuracy for PRICE (done)
I used the speech recognition to help generate text commands and find out that it would give price in two formats ($xx, or xx dollars). I tests both cases with randomly generated money value, and the spacy model could recognize it correctly with 100% accuracy. Price is very important when adding entries.
- Test parsing accuracy for ITEM
Like before, I would use about 50 commands to test if our trained model could accurately parse the item out of the sentence.