Browse Teach Curate

Automatic Evaluation Metrics for Natural Language Generation

Quantitative measures of how good machine-generated text is: n-gram overlap metrics such as BLEU, embedding-based similarity such as cosine similarity, and the limitations of automatic metrics relative to human judgement.

jeremy Video

Neural Framework for State-of-the-art Machine Translation Evaluation in Unbabel

The core theory presented is Cross-lingual Optimized Metric for Evaluation of Translation (COMET), a neural framework designed to approximate human translation quality judgments by leveraging pre-tra…