Automatic Evaluation Method

Summary

Automatic evaluation methods usually come into place where there is no ground truth or the labeled data is very expensive. This topic has been developed a lot since last decade, and showed its applicability in many different NLP tasks.

Main Ideas

The main ideas behind automatic evaluation methods (or metrics) is that there is an alternative measure A to the original measure B. The measure B requires ground truth (or labeled data) where usually measure A does not require ground truth (or a small set of it).

A few example of alternative measures are

• Entropy, it measures how well is the mapping function between two sets and serves in the cases that the mapping function is a crucial indicator of the overall performance.
• N-gram statistics, it measures how n-gram patterns are formed in the output text, which performs well as an alternative measure for text generation tasks.

The proof of applicability for automatic evaluation methods in different task usually starts with a hypothesis and requires a correlation analysis of the alternative measure with original measure.

Automatic Evaluation For Machine Translation

The most famous application of automatic evaluation is the BLEU score for machine translation which takes the