Ever wondered how computers know if a translation makes sense?

Image: The original uploader was Palmiped at English Wikipedia., CC BY 3.0, via Wikimedia Commons

BLEU

Ever wondered how computers know if a translation makes sense?

Imagine you're using a translation app to understand a foreign movie's subtitles. You want to make sure the subtitles are accurate and readable.

Think of BLEU as a scorecard that compares the app's translation to a set of professional translations, giving you a sense of how good it is.

Example

If the app's translation closely matches the professional ones, it gets a high BLEU score, indicating better quality.

Remember this

BLEU score helps you quickly gauge the accuracy of machine translations.

Text adapted from Wikipedia, licensed under CC BY-SA 4.0.

Related concepts

Evaluation of machine translation

Can we truly measure how good a machine translation is?

BLEU vs ROUGE: BLEU measures precision of n-grams, ROUGE measures recall

BLEU measures precision of n-grams, ROUGE measures recall

Precision and recall

Precision = Relevant retrieved instances / All retrieved instances

self-attention: Attention(Q,K,V) = softmax(QK^T/√d_k)V

Ever wondered how computers understand what's important in a sentence?

Write the attention score formula before softmax: e_ij = a(s_i, h_j)

How do we know what's important in a sentence?

TF-IDF scoring

TF-IDF = (Term Frequency) * (Inverse Document Frequency)

Swipe through 100 ML concepts daily