Compare commits
6 Commits
Author | SHA1 | Date | |
---|---|---|---|
|
975dd50258 | ||
|
64b2612ef1 | ||
|
dfe830ac26 | ||
|
20d03b9e18 | ||
|
140f4c0284 | ||
|
02ee0ff2fa |
21038
dev-0/out.tsv
21038
dev-0/out.tsv
File diff suppressed because it is too large
Load Diff
75
kenlm_run.py
Normal file
75
kenlm_run.py
Normal file
@ -0,0 +1,75 @@
|
||||
from tqdm import tqdm
|
||||
import regex as re
|
||||
from nltk.tokenize import word_tokenize
|
||||
from english_words import get_english_words_set
|
||||
import kenlm
|
||||
from math import log10
|
||||
import pickle
|
||||
|
||||
path = 'kenlm_model.binary'
|
||||
model = kenlm.Model(path)
|
||||
|
||||
with open('V.pickle', 'rb') as handle:
|
||||
V_counter = pickle.load(handle)
|
||||
|
||||
def clean_string(text):
|
||||
text = text.lower()
|
||||
text = re.sub(r" -\\*\\n", "", text)
|
||||
text = re.sub(r"\\n", " ", text)
|
||||
text = text.strip()
|
||||
return text
|
||||
|
||||
|
||||
def predict_probs(w1, w2, w4, w5):
|
||||
best_scores = []
|
||||
pred_str = ""
|
||||
for word in V_counter:
|
||||
text = ' '.join([w1, w2, word, w4, w5])
|
||||
text_score = model.score(text, bos=False, eos=False)
|
||||
if len(best_scores) < 5:
|
||||
best_scores.append((word, text_score))
|
||||
else:
|
||||
worst_score = best_scores[-1]
|
||||
if worst_score[1] < text_score:
|
||||
best_scores[-1] = (word, text_score)
|
||||
best_scores = sorted(best_scores, key=lambda tup: tup[1], reverse=True)
|
||||
|
||||
for word, prob in best_scores:
|
||||
pred_str += f'{word}:{prob} '
|
||||
pred_str += f':{log10(0.99)}'
|
||||
return pred_str
|
||||
|
||||
def get_word_predictions(w1, w2,):
|
||||
for word in get_english_words_set(['web2'], lower=True):
|
||||
sentence = f'{w1} {word} {w2}'
|
||||
text_score = model.score(sentence, False, False)
|
||||
yield((word, text_score))
|
||||
|
||||
def argmax(w1,w2):
|
||||
top_10 = sorted(list(get_word_predictions(w1,w2)), key=lambda x: -x[1])[:4]
|
||||
output_line = " ".join(["{}:{:.8f}".format(w, p) for w, p in top_10])
|
||||
return output_line
|
||||
|
||||
def run_predictions(source_folder):
|
||||
with open(f"{source_folder}/in.tsv", encoding="utf8", mode="rt") as file:
|
||||
train_data = file.readlines()
|
||||
|
||||
with open(f"{source_folder}/out.tsv", "w", encoding="utf-8") as output_file:
|
||||
for line in tqdm(train_data):
|
||||
line = line.split("\t")
|
||||
|
||||
l1 = clean_string(line[-2])
|
||||
l2 = clean_string(line[-1])
|
||||
|
||||
if not l1 or not l2:
|
||||
out_line = "the:0.5 a:0.3 :0.2"
|
||||
else:
|
||||
w1, w2 = word_tokenize(l1)[-2:]
|
||||
w3, w4 = word_tokenize(l2)[:2]
|
||||
out_line = predict_probs(w1, w2, w3, w4)
|
||||
|
||||
output_file.write(out_line + "\n")
|
||||
|
||||
|
||||
run_predictions("dev-0")
|
||||
run_predictions("test-A")
|
13
lm0.py
13
lm0.py
@ -1,13 +0,0 @@
|
||||
#!/usr/bin/python3
|
||||
import sys
|
||||
for i, line in enumerate(sys.stdin):
|
||||
if(line.split('\t')[6].endswith('\n')):
|
||||
print('hence:0.95 :0.05')
|
||||
elif(line.split('\t')[6].endswith('ot')):
|
||||
print('be:0.6 a:0.35 :0.05')
|
||||
elif(line.split('\t')[6].endswith('.')):
|
||||
print('but:0.85 :0.15')
|
||||
elif([l.split(' ') for l in line.split('\t')][5][0].endswith('ing')):
|
||||
print('this:0.88 :0.12')
|
||||
else:
|
||||
print('the:0.5 a:0.3 :0.2')
|
7414
test-A/out.tsv
Normal file
7414
test-A/out.tsv
Normal file
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue
Block a user