Across
- 3. Stemmer A classic stemming algorithm used in English NLP
- 5. Automata Regular expressions belong to this class of automata
- 6. Dataset used for training word-level NLP models
- 7. Morphological process that creates new words (e.g., nation → national)
- 9. The smallest meaningful linguistic unit in a corpus
Down
- 1. A statistical model for computing the likelihood of a word based on the previous one
- 2. Simpler form of morphological analysis that chops off word endings
- 4. Words that occur together more often than expected by chance
- 5. A finite automaton that produces an output string while reading input
- 8. Distance A method to measure how different two strings are