我們正在嘗試使用來自vowpal-wabbit的Learning2Search for NER 我們正在使用ATIS數據集。NER的Learning2Search(vowpal-wabbit)給出奇怪的結果
在ATIS中有127個實體(包括其他類別) 訓練集有4978個測試有893個句子。
如何過,當我們在測試中運行它設置它映射的一切無論是1級(航空公司名稱)或2類(機場代碼) 這是有線。
我們嘗試了其他數據集(https://github.com/glample/tagger/tree/master/dataset),相同的行爲。
看起來我沒有用正確的方法。任何指針都會有很大的幫助。
代碼片段:
with open("/tweetsdb/ner/datasets/atis.pkl") as f:
train, test, dicts = cPickle.load(f)
idx2words = {v: k for k, v in dicts['words2idx'].iteritems()}
idx2labels = {v: k for k, v in dicts['labels2idx'].iteritems()}
idx2tables = {v: k for k, v in dicts['tables2idx'].iteritems()}
#Convert the dataset into a format compatible with Vowpal Wabbit
training_set = []
for i in xrange(len(train[0])):
zip_label_ent_idx = zip(train[2][i], train[0][i])
label_ent_actual = [(int(i[0]), idx2words[i[1]]) for i in zip_label_ent_idx]
training_set.append(label_ent_actual)
# Do like wise to get test chunk
class SequenceLabeler(pyvw.SearchTask):
def __init__(self, vw, sch, num_actions):
pyvw.SearchTask.__init__(self, vw, sch, num_actions)
sch.set_options(sch.AUTO_HAMMING_LOSS | sch.AUTO_CONDITION_FEATURES)
def _run(self, sentence):
output = []
for n in range(len(sentence)):
pos,word = sentence[n]
with self.vw.example({'w': [word]}) as ex:
pred = self.sch.predict(examples=ex, my_tag=n+1, oracle=pos, condition=[(n,'p'), (n-1, 'q')])
output.append(pred)
return output
vw = pyvw.vw("--search 3 --search_task hook --ring_size 1024")
代碼訓練模型:
#Training
sequenceLabeler = vw.init_search_task(SequenceLabeler)
for i in xrange(3):
sequenceLabeler.learn(training_set[:10])
代碼預測:
pred = []
for i in random.sample(xrange(len(test_set)), 10):
test_example = [ (999, word[1]) for word in test_set[i] ]
test_labels = [ label[0] for label in test_set[i] ]
print 'input sentence:', ' '.join([word[1] for word in test_set[i]])
print 'actual labels:', ' '.join([str(label) for label in test_labels])
print 'predicted labels:', ' '.join([str(pred) for pred in sequenceLabeler.predict(test_example)])
要查看完整的代碼,請參閱本筆記本: https://github.com/nsanthanam/ner/blob/master/vowpal_wabbit_atis.ipynb