Day 4: Analyzing Grammar
Grammatical Complexity and NLP Tools
Overview
Day 4 introduces grammatical analysis in corpus linguistics, exploring complexity measures and computational tools for parsing and analysis.
Key Concepts
- Grammatical complexity
- Predictive measures versus Descriptive measures
- POS tagging
- Dependency parsing
- Precision, Recall, and F1 score
- Syntactic sophistication and fine-grained measures
Preparation
Before Day 4:
- Read:
- Durrant Ch. 5
- Kyle, K., & Crossley, S. A. (2018). Measuring Syntactic Complexity in L2 Writing Using Fine‐Grained Clausal and Phrasal Indices. The Modern Language Journal, 102(2), 333–349.
- Skim:
- Durrant Ch. 6 (Ignore R codes if you are not familiar)
Schedule
| Time | Activity |
|---|---|
| 10:30-12:00 | Session 10: Grammar — Overview |
| 12:00-13:00 | Lunch |
| 13:00-14:30 | Session 11: POS Tagging and Parsing |
| 14:30-14:40 | Break |
| 14:40-16:10 | Session 12: Linguistic Complexity Analysis |
| 16:10-17:00 | Office Hour (You can ask questions.) |
Assignments
- Due 8/8 (Fri): Corpus Lab Assignment 4
- Complete grammatical analysis exercises using Python notebooks and TagAnt