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():

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))

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):

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

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.