Encoder-Decoder zero shot domain (skill), intent, and entity tagging NLU model with a zero-shot NLG for generating voice assistant responses. All in one!
Apache License 2.0
1
stars
0
forks
source link
Analysis: Benchmark Comparison for Snips and Other Taggers #6
Benchmark Snips and other open-source intent and entity taggers on a subset of the dataset used for the T5-based model. Compare the performance to understand how well the traditional taggers stack up against the zero-shot approach.
DoD
[ ] Select a representative subset of the dataset.
[ ] Run Snips and other taggers on this subset.
[ ] Summarize the benchmark results with key metrics.
Description
Benchmark Snips and other open-source intent and entity taggers on a subset of the dataset used for the T5-based model. Compare the performance to understand how well the traditional taggers stack up against the zero-shot approach.
DoD