neubig

#!/usr/bin/python

################################################################################
# pequalnp.py
#  Graham Neubig
#  4/1/2014
#
# This is a program that provides an answer for the age-old problem of whether
# the class of problems that can be verified in polynomial time (NP) is equal
# to the class of problems for which an answer can be provided in polynomial

neubig

#!/usr/bin/perl

use strict;
use utf8;
use List::Util qw(max min);
binmode STDIN, ":utf8";
binmode STDOUT, ":utf8";

if(@ARGV != 2) {
    print STDERR "Usage: counterrors.pl REFERENCE SYSTEM\n";

neubig

set.seed(123141)

fcount <- 20
tcount <- 1
alpha <- 3
xf <- rnorm(fcount,mean=-1, sd=0.7)
xt <- rnorm(tcount,mean=1, sd=0.7)
yf <- mat.or.vec(fcount,1)
yt <- mat.or.vec(tcount,1)

neubig

#include <vector>
#include <iostream>
#include <cstdlib>
#include <cmath>

using namespace std;

int SampleMultinomial(const vector<double> & distribution) {
    double value = (double)rand()/RAND_MAX;
    for(int i = 0; i < distribution.size(); i++)

neubig

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import sys
import re
import datetime

pattern = ur'電力.*供給'

neubig

#!/usr/bin/python
# ***************************
# * solve-3sat.py
# *  by Graham Neubig
# *  4/1/2013
# ***************************
#
# This is a Python program to provide an answer for satisfiability problems
# in conjunctive normal form with 3 variables per clause (3SAT) in LINEAR time.
#

neubig

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# This is a simplified implementation of the LSTM language model (by Graham Neubig)
#
#  LSTM Neural Networks for Language Modeling
#  Martin Sundermeyer, Ralf Schlüter, Hermann Ney
#  InterSpeech 2012
# 
# The structure of the model is extremely simple. At every time step we

neubig

"""
DyNet implementation of a sequence labeler (POS taggger).
This is a translation of this tagger in PyTorch: https://gist.github.com/hal3/8c170c4400576eb8d0a8bd94ab231232

Basic architecture:
 - take words
 - run though bidirectional GRU
 - predict labels one word at a time (left to right), using a recurrent neural network "decoder"
The decoder updates hidden state based on:
 - most recent word

neubig

#!/usr/bin/python

# A python implementation of the string rewriting kernel
#  by Graham Neubig
#
# Reference:
#  Fan Bu, Hang Li, Xiaoyan Zhu. "String Rewriting Kernel". ACL 2012
#  http://aclweb.org/anthology-new/P/P12/P12-1047.pdf

from math import factorial

neubig

#!/usr/bin/python

# This code implements the training part of the Restricted Boltzmann Machine
# language model described by:
#   Three New Graphical Models for Statistical Language Modeling
#   Andriy Mnih and Geoffrey Hinton
#   ICML 2007
#   http://www.gatsby.ucl.ac.uk/~amnih/papers/threenew.pdf
#
# Usage: train-rbmlm.py training-file.txt