minhlab

from collections import Counter
import numpy as np
from scipy.stats import pearsonr

train = 'output/dep/penntree.jk.sd/train.mrg.dep'
ref = 'output/dep/penntree.jk.sd/valid.mrg.dep'
sys = 'output/dep/sd_parse-published-model_valid.conll'
out_path = 'output/occurrence-performance.npy'
count_path = 'output/occurrence-counts.npy'

minhlab

import numpy as np

# from deep-coref project: https://github.com/clarkkev/deep-coref
# download w2v_50d.txt from here: https://drive.google.com/file/d/0B5Y5rz_RUKRmdEFPcGIwZ2xLRW8/view
with open('w2v_50d.txt') as f:
    word2id = {}
    vectors = []
    words = []
    for line in f:
        parts = line.strip().split()

minhlab

import numpy as np
import sys

def zero_safe_normalization(a):
    norms = np.sum(a*a, axis=1)
    zero_indices = np.nonzero(norms == 0)[0].tolist()
    if zero_indices:
        sys.stderr.write('Detect %d zero norms: %s\n' %(len(zero_indices), str(zero_indices)))
        norms[zero_indices] = 1.0 # don't worry, 0/1 = 0
    a /= norms[:,np.newaxis]

minhlab

# -*- coding: utf-8 -*-

import pywikibot
import sys
from collections import Counter
from random import randint

wiki = 'wikipedia'
lang = 'vi'

minhlab

{
   "loss":{
      "y":"summed_cross_entropy",
      "anaphoricities":"summed_cross_entropy"
   },
   "theano_mode":null,
   "name":"Graph",
   "output_config":[
      {
         "inputs":[

minhlab

from theano import function, config, shared, tensor
import numpy
import time

vlen = 10 * 30 * 768  # 10 x #cores x # threads per core
iters = 1000

rng = numpy.random.RandomState(22)
x = shared(numpy.asarray(rng.rand(vlen), config.floatX))
f = function([], tensor.exp(x))

minhlab

import os
import re
count = 0
for root, dir_names, file_names in os.walk('ECB+'):
    for fname in file_names:
        if 'plus' not in fname:
            path = os.path.join(root, fname)
            with open(path) as f:
                content = f.read()
                print list(m.group() for m in re.finditer('<token', content))

minhlab

import os
import re
count = 0
for root, dir_names, file_names in os.walk('ECB+'):
    for fname in file_names:
        if 'plus' in fname:
            path = os.path.join(root, fname)
            with open(path) as f:
                content = f.read()
                print list(m.group() for m in re.finditer('<token', content))

minhlab

import java.util.*;
import java.lang.*;
import java.io.*;

/* Name of the class has to be "Main" only if the class is public. */
class Ideone
{
	public static void main (String[] args) throws java.lang.Exception
	{
		double a = Math.random();

minhlab

local MaskedLogSoftMax, Parent = torch.class('nn.MaskedLogSoftMax', 'nn.Module')

function MaskedLogSoftMax:__init(masks, filler)
    Parent.__init(self)
    self.masks = masks
    self.minvals = torch.Tensor()
    self.mininds = torch.LongTensor() 
    self.temp1 = torch.Tensor()
    self.temp2 = torch.Tensor()