File size: 2,437 Bytes
98dc5b0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
from typing import List, Tuple
import itertools
from sklearn.metrics.pairwise import cosine_similarity
import numpy as np
#Maximal Marginal Relevance origin: https://maartengr.github.io/KeyBERT/api/mmr.html
def mmr(doc_embedding: np.ndarray,
word_embeddings: np.ndarray,
words: List[str],
top_n: int = 5,
diversity: float = 0.9) -> List[Tuple[str, float]]:
""" Calculate Maximal Marginal Relevance (MMR)
between candidate keywords and the document.
MMR considers the similarity of keywords/keyphrases with the
document, along with the similarity of already selected
keywords and keyphrases. This results in a selection of keywords
that maximize their within diversity with respect to the document.
Arguments:
doc_embedding: The document embeddings
word_embeddings: The embeddings of the selected candidate keywords/phrases
words: The selected candidate keywords/keyphrases
top_n: The number of keywords/keyhprases to return
diversity: How diverse the select keywords/keyphrases are.
Values between 0 and 1 with 0 being not diverse at all
and 1 being most diverse.
Returns:
List[Tuple[str, float]]: The selected keywords/keyphrases with their distances
"""
# Extract similarity within words, and between words and the document
word_doc_similarity = cosine_similarity(word_embeddings, doc_embedding)
word_similarity = cosine_similarity(word_embeddings)
# Initialize candidates and already choose best keyword/keyphras
keywords_idx = [np.argmax(word_doc_similarity)]
candidates_idx = [i for i in range(len(words)) if i != keywords_idx[0]]
for _ in range(top_n - 1):
# Extract similarities within candidates and
# between candidates and selected keywords/phrases
candidate_similarities = word_doc_similarity[candidates_idx, :]
target_similarities = np.max(word_similarity[candidates_idx][:, keywords_idx], axis=1)
# Calculate MMR
mmr = (1-diversity) * candidate_similarities - diversity * target_similarities.reshape(-1, 1)
mmr_idx = candidates_idx[np.argmax(mmr)]
# Update keywords & candidates
keywords_idx.append(mmr_idx)
candidates_idx.remove(mmr_idx)
return [(words[idx], round(float(word_doc_similarity.reshape(1, -1)[0][idx]), 4)) for idx in keywords_idx] |