Lesk Algorithm

Lesk Algorithm

• used for Word Sense Disambiguation (WSD)
• use dictionary or thesaurus as indirect kind of supervision. choose the sense whose gloss shares the most words with target word neighborhood

Lesk Algorithm

# returns best sense of word
def simplified_lesk(word, sentence):
	best_sense = most_frequent_sense_for(word)
	max_overlap = 0
	context = set_of_words_in(sentence)
	for sense in senses_of(word):
		signature = set_of_words_in_gloss_and_example_sentences_of(sense)
		overlap = compute_overlap(signature, context)
		if overlap > max_overlap:
			max_overlap = overlap
			best_sense = sense
	return best_sense

Lesk Algorithm - Example

Click here to expand...

given sentence:

• The bank can guarantee deposits will eventually cover future tuition costs because it invests in adjustable-rate mortgage securities

find sense of bank

below is the gloss and examples sentences of the word bank:

bank1	gloss	a financial institution that accepts deposits and channels the money into lending activities
	examples	he cashed a check at the bank that bank holds the mortgage on my home
bank2	gloss	sloping land (especially the slope besides a body of water)
	examples	they pulled the canoe up on the bank he sat on the bank of the river and watched the currents

based on the Lesk Algorithm, we have:

• bank¹- 2 content words overlap
• bank²- 0 content words overlap

thus, we choose bank¹ as the most probable sense used in the sentence

Lesk Algorithm - Improvements

• include related words (i.e. hyponyms)
• apply a weight to each overlapping word
• inverse document frequency (idf) value