quadrismegistus

def smart_procrustes_align_gensim(base_embed, other_embed, words=None):
	"""Procrustes align two gensim word2vec models (to allow for comparison between same word across models).
	Code ported from HistWords <https://github.com/williamleif/histwords> by William Hamilton <wleif@stanford.edu>.
		(With help from William. Thank you!)

	First, intersect the vocabularies (see `intersection_align_gensim` documentation).
	Then do the alignment on the other_embed model.
	Replace the other_embed model's syn0 and syn0norm numpy matrices with the aligned version.
	Return other_embed.

mbollmann

# Source:
# https://github.com/farizrahman4u/seq2seq/blob/master/seq2seq/layers/state_transfer_lstm.py

from keras import backend as K
from keras.layers.recurrent import LSTM

class StateTransferLSTM(LSTM):
    """LSTM with the ability to transfer its hidden state.

    This layer behaves just like an LSTM, except that it can transfer (or

basaundi

#!/usr/bin/env python
# Ander Martinez Sanchez

from __future__ import division, print_function
from math import exp, log
from collections import Counter


def ngram_count(words, n):
    if n <= len(words):

MajorTal

from numpy.random import choice as random_choice, randint as random_randint, rand
MAX_INPUT_LEN = 40
AMOUNT_OF_NOISE = 0.2 / MAX_INPUT_LEN
CHARS = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ .")

def add_noise_to_string(a_string, amount_of_noise):
    """Add some artificial spelling mistakes to the string"""
    if rand() < amount_of_noise * len(a_string):
        # Replace a character with a random character
        random_char_position = random_randint(len(a_string))

odashi

#!/usr/bin/python3

import math
import random
import sys
from argparse import ArgumentParser
from collections import defaultdict
from util.functions import trace

def parse_args():

odashi

# usage (single sentence):
#   ref = ['This', 'is', 'a', 'pen', '.']
#   hyp = ['There', 'is', 'a', 'pen', '.']
#   stats = get_bleu_stats(ref, hyp)
#   bleu = calculate_bleu(stats) # => 0.668740
#
# usage (multiple sentences):
#   stats = defaultdict(int)
#   for ref, hyp in zip(refs, hyps):
#     for k, v in get_bleu_stats(ref, hyp).items():

entron

'''This scripts implements Kim's paper "Convolutional Neural Networks for Sentence Classification"
with a very small embedding size (20) than the commonly used values (100 - 300) as it gives better
result with much less parameters.

Run on GPU: THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python imdb_cnn.py

Get to 0.853 test accuracy after 5 epochs. 13s/epoch on Nvidia GTX980 GPU.
'''

from __future__ import print_function

odashi

#!/usr/bin/python3

import datetime
import sys
import math
import numpy as np
from argparse import ArgumentParser
from collections import defaultdict

from chainer import FunctionSet, Variable, functions, optimizers

kachayev

Channels Are Not Enough

... or Why Pipelining Is Not That Easy

Golang Concurrency Patterns for brave and smart.

By @kachayev

Intro

syllog1sm

"""A simple implementation of a greedy transition-based parser. Released under BSD license."""
from os import path
import os
import sys
from collections import defaultdict
import random
import time
import pickle

SHIFT = 0; RIGHT = 1; LEFT = 2;