HardNLPnlp-404

BM25 Term Score Contribution

Problem

The BM25 contribution of one query term is idf * tf (k1 + 1) / (tf + k1 (1 - b + b * dl / avgdl)).

Given the term frequency, document length, average document length, IDF, k1, and b, return the contribution.

Hint

Length normalization uses the ratio of document length to the average.

case 1

in: [3,50,40,2,1.2,0.75]

expected: 2.9830508474576276

case 2

in: [1,100,50,1,1.2,0.75]

expected: 0.7096774193548387

case 3

in: [5,10,10,3,1.5,0.5]

expected: 5.769230769230769

Starter codePython

def bm25_term_score_contribution(tf, doc_length, avgdoc_length, idf, k1, b):
    # Your code here
    pass

3 test cases · run your code against them in the editor