Intrinsic Performance Measure

An Intrinsic Performance Measure is a predictive performance measure that is applied to a predictive benchmark tasks.

• AKA: Offline Performance.
• Context:
  • It can correlate with an Extrinsic Performance Measure (which reports on real-world performance).
  • ...
• Example(s):
  • a Intrinsic Classification Performance Measure, such as: accuracy, recall, F1, perplexity.
  • an Intrinsic NLG Measure, such as: ROUGE.
  • …
• Counter-Example(s):
  • an Extrinsic Performance Measure, such as: Lives Saved Measure, Time Saved Measure, Money Saved Measure.
• See: Empirical Analysis.

---

---

References

2009

• (Jurafsky & Martin, 2009) ⇒ Daniel Jurafsky, and James H. Martin. (2009). “Speech and Language Processing, 2nd edition." Pearson Education. ISBN:0131873210
  • … Thus, we wold like a metric that can be used to quickly evaluate potential improvements in a language model. An intrinsic evaluation metric is one that measures the quality of a model independent of any application. Perplexity is the most common intrinsic evaluation metric for N-gram language models.

---