added wsd_method 1

scripts/wsd/wsd_method1_nadia_confusion.py → scripts/wsd/wsd_method1.py

@@ -145,7 +145,8 @@ def get_distance(node_combi, dist_dict):
 
 def map_distances(sentence, embed_dict):
 	"""
-	
+	this function computes every distance between a word and all senses of other words
+	returns a dictionary {(id1,id2):distance,...}
 	"""
 	dist_dict ={}
 	for i in range(len(sentence[:-1])):
@@ -158,7 +159,7 @@ def map_distances(sentence, embed_dict):
 
 def find_optimum(sentence, dist_dict):
 	"""
-	
+	this function finds the optimal sense combination of words in a sentence
 	"""
 	optimum = [0,0]
 	for n_combi in node_combi(sentence):
@@ -171,13 +172,11 @@ def find_optimum(sentence, dist_dict):
 	return optimum
 
 
-def map_sense():
+def node_combi(sentence):
 	"""
-	
+	IN:[int]
+	this function computes every possible sense combination of a given sentence
 	"""
-
-def node_combi(sentence):
-
 	for combi in itertools.product(*sentence):
 		yield combi
 
@@ -193,10 +192,11 @@ def write_answer_to_file(data, filename):
 
 def iterate_over(senseval_data, label_embeddings, lemmata_mapping, id_mapping, sense_key_mapping):
 	"""
-	
+	this function iterates over sentences in senseval data 
+	computes the optimal combination of senses given a sentence
 	"""
 	ambig_sents = open_mapping(senseval_data)
-	
+	# split sentence if it contains more than 6 words
 	for i, sent in enumerate(ambig_sents):
 		if len(sent) >=6:
 			ambig_sents[i] = sent[:6]
@@ -204,12 +204,16 @@ def iterate_over(senseval_data, label_embeddings, lemmata_mapping, id_mapping, s
 
 	sentences = [[[word['lemma'],word['pos'],word['key']] for word in sent] for sent in ambig_sents]
 	solutions = []
+
 	for sentence in sentences:
 		mapped_sent = map_words(sentence, lemmata_mapping)[0]
 		lemma_list = map_words(sentence, lemmata_mapping)[1]
+
+		# check if compound word were splitted in two
 		split = 0
 		if len(sentence) < len(mapped_sent):
 			split = len(mapped_sent) - len(sentence)
+		# saves the index of an unknown word and removes it from mapped_sent
 		no_key = []
 		for word in mapped_sent:
 			if word[0]=='U': 
@@ -217,36 +221,33 @@ def iterate_over(senseval_data, label_embeddings, lemmata_mapping, id_mapping, s
 
 		mapped_sent = [word for word in mapped_sent if word[0]!='U']
 
+		# computes label embeddings for every node and saves them in a dict
 		embed_dict = embed(mapped_sent, label_embeddings)
-
+		# computes distances between nodes and saves them in to a dict
 		dist_dict = map_distances(mapped_sent, embed_dict)
-
+		# computes the optimal sense combination
 		optimum = find_optimum(mapped_sent, dist_dict)
-
+		# maps node id's to wn 3 synset id's
 		optimum = [id_mapping[str(o)] for o in optimum[1]]
 
-		# map syn id to sense_key
+		# map synset id to sense_key
 		for i, o in enumerate(optimum):
 			key = tuple(o + [lemma_list[i]])
 			if key in sense_key_mapping.keys():
 				optimum[i] = sense_key_mapping[key]
 			else: optimum[i] = ''
-
+		# adds the removed unknown words
 		if len(no_key) != 0:
 			for el in no_key:
 				optimum.insert(el, '')
-
+		# resplits compound words
 		resplit = 0
-
 		for i, word in enumerate(sentence):
 			if split != 0:
 				if '-' in word[0]:
 					optimum[i] = optimum[i] + ' ' + optimum[i+1]
 					optimum.remove(optimum[i+1])
 					split -= 1
-		#print(sentence)
-		#print(mapped_sent)
-		#print(optimum)
 
 		solution_sent = [(word[2],optimum[k]) for k, word in enumerate(sentence)]
 		solutions += solution_sent
@@ -262,7 +263,7 @@ if __name__ == '__main__':
 
 	sense_key_mapping = open_sense_keys(SENSE_KEY_MAPPING)
 
-	solutions = iterate_over(SENSEVAL_2, label_embeddings, lemmata_mapping, sense_key_mapping)
+	solutions = iterate_over(SENSEVAL_2, label_embeddings, lemmata_mapping, id_mapping sense_key_mapping)
 	write_answer_to_file(solutions, OUTPUT2)