From 201549dd7dde89f64ab5db6c10aba83d60302b81 Mon Sep 17 00:00:00 2001
From: Victor Zimmermann <zimmermann@cl.uni-heidelberg.de>
Date: Tue, 6 Mar 2018 16:23:09 +0100
Subject: [PATCH] Added backup dummy (and singleton clustering if no sense
matches or no sense was found for the time being).
---
code/absinth_nx.py | 44 +++++++++++++++++++++++++++++++-------------
1 file changed, 31 insertions(+), 13 deletions(-)
diff --git a/code/absinth_nx.py b/code/absinth_nx.py
index 54667b4..57cae2f 100644
--- a/code/absinth_nx.py
+++ b/code/absinth_nx.py
@@ -8,6 +8,7 @@ from copy import deepcopy
import numpy as np # for calculations
nlp = spacy.load('en') # standard english nlp
+
def frequencies(corpus_path, target, stop_words=['utc', 'new', 'other'], allowed_tags=['NN','NNS','JJ','JJS','JJR','NNP'], min_context_size = 4, max_nodes=10000, max_edges=1000000):
node_freq = dict()
@@ -142,6 +143,7 @@ def root_hubs(graph, edge_freq, min_neighbors=4, theshold=0.8):
return H
+
#Components algorithm from Véronis (2004), converts graph for target into a MST
def components(graph, hubs, target):
@@ -167,7 +169,8 @@ def disambiguate(mst, hubs, contexts):
T = mst
H = hubs
- cluster = []
+ backup_cluster = len(H)
+ result = []
for v in list(T.nodes):
@@ -196,24 +199,36 @@ def disambiguate(mst, hubs, contexts):
idx = contexts.index(c) + 1
- try:
- cluster.append((np.argmax(vector), idx))
- except:
- cluster.append((len(H), idx))
-
- return cluster
+ if max(vector) == 0:
+ result.append((backup_cluster, idx))
+ backup_cluster += 1
+ else:
+ try:
+ cluster = np.argmax(vector)
+ result.append((cluster, idx))
+ except:
+ result.append((backup_cluster, idx))
+ backup_cluster += 1
+
+ return result
+def backup(contexts):
+
+ pass
+
+
if __name__ == '__main__':
- data_path = '/home/students/zimmermann/Courses/ws17/fsem/absinth/WSI-Evaluator/datasets/MORESQUE'
+ data_path = '/home/students/zimmermann/Courses/ws17/fsem/absinth/WSI-Evaluator/datasets/MORESQUE/'
#corpus_path = '/home/students/zimmermann/Courses/ws17/fsem/absinth/test'
- corpus_path = '/proj/absinth/wikipedia.txt.dump.20140615-en.SZTAKI'
+ corpus_path = '/proj/absinth/wikipedia.txt.dump.20140615-en.SZTAKI/'
+ results_path = '/home/students/zimmermann/Courses/ws17/fsem/absinth/results/'
results = dict()
- with open(data_path+'/results.txt', 'r') as results_file:
+ with open(data_path+'results.txt', 'r') as results_file:
for line in results_file.readlines()[1:]:
@@ -228,19 +243,22 @@ if __name__ == '__main__':
topics = dict()
- with open(data_path+'/topics.txt', 'r') as topics_file:
+ with open(data_path+'topics.txt', 'r') as topics_file:
+
+ already_processed = [f.replace('.absinth', '') for f in os.listdir(results_path)]
for line in topics_file.readlines()[1:]:
l = line.split('\t')
- topics[l[0]] = l[1]
+ if l[1] not in already_processed:
+ topics[l[0]] = l[1]
for key, value in topics.items():
target = value.strip()
print("[A] Processing '"+target+"'.\n")
- f = open('/home/students/zimmermann/Courses/ws17/fsem/absinth/results/'+target+'.absinth', 'w')
+ f = open(results_path+target+'.absinth', 'w')
f.write('subTopicID\tresultID\n')
print('[A] Counting Tokens...')
--
GitLab