For further actions, you may consider blocking this person and/or reporting abuse
Read next
Late Chunking: Boosting Contextual Chunk Representations with Long-Context Language Models
Mike Young -
Top Models Tackle Billion-Scale Nearest Neighbor Search at NeurIPS'23
Mike Young -
Unraveling Package Hallucinations: A Comprehensive Analysis of Code-Generating LLMs
Mike Young -
Day: 25 Optimizer Algorithms for Large Language Models (LLMs)
Naresh Nishad -
Top comments (1)
I'm no machine learning expert (not even by a longshot), but I think it would be a good start to split words by their vowels. The syllables of a word are usually separated by its vowels. The key word is usually.
Then, you can train a neural network to split words by their vowels and identify syllables from the split sections. Further trial and error will allow the neural network to correctly split a word by its syllables. It will also be able to know whether or not a group of letters that happen to be separated by vowels are syllables.
Finally, you can train the network to identify compound words. By doing that, the network can automatically identify syllables already—that being the components of a compound word.