evanmiltenburg

import requests
import re
import time

r = requests.get('https://direct.mit.edu/books/book/5244/The-Open-Handbook-of-Linguistic-Data-Management',
                 stream=True, headers={'User-agent': 'Mozilla/5.0'})
                 
urls = re.findall('href="(.*?.pdf)"', r.text)
base = 'https://direct.mit.edu'
urls = [base + path for path in urls if '/book/' in path]

evanmiltenburg

import spacy

nlp = spacy.load('nl_core_news_sm')

with open('bordewijk.txt') as f:
    doc = nlp(f.read())

people = [ent.orth_ for ent in doc.ents if ent.label_ == 'PERSON']

print(people)

evanmiltenburg

import xlsxwriter

# Create workbook with a new worksheet.
workbook = xlsxwriter.Workbook('hello.xlsx')
worksheet = workbook.add_worksheet()

# Write the tokens.
worksheet.write('A1', 'Hello')
worksheet.write('B1', 'world')
worksheet.write('C1', '!')

evanmiltenburg

def get_lengths(num_lines, line_length):
    "Get n lines, totaling a particular length."
    lengths = np.random.random(num_lines)
    lengths *= line_length / np.sum(lengths)
    return lengths

def lines(line_length, page_width):
    "Get a random number of lines, with n-1 gaps of varying length in between."
    num_lines = np.random.randint(1,10)
    lengths = get_lengths(num_lines, line_length)

evanmiltenburg

\documentclass[12pt]{standalone}
\usepackage{tgtermes}
\usepackage{tgheros}
\usepackage[T1]{fontenc}

\usepackage{tikz}
\usetikzlibrary{arrows}
\usetikzlibrary{arrows.meta}
\usetikzlibrary{calc}

evanmiltenburg

import matplotlib.pyplot as plt
import seaborn as sns

from matplotlib.lines import Line2D

my_palette = sns.color_palette("cubehelix", 3)
sns.set_palette(my_palette)

def legend_circles(labels, palette, loc=1, markersize=10, marker='o', padding=0):
    "Make a legend where the color is indicated by a circle."

evanmiltenburg

Papers at INLG

Here's a list of all the papers presented at INLG 2017, sourced from here. I made this list because it's easier to read and print.

Please refer to the INLG website for the official schedule, which may be subject to change, and also contains other events, like invited talks and the hackathon.

Tuesday

evanmiltenburg

import csv
import numpy as np
from gensim.models import Word2Vec

np.random.seed(1234)

from keras.models import Sequential
from keras.layers.core import Activation, Dense
from keras.callbacks import EarlyStopping

evanmiltenburg

from collections import Counter
import re
import glob

class ConllEntry:
    def __init__(self, id, form, pos, cpos, parent_id=None, relation=None):
        self.id = id
        self.form = form
        self.norm = normalize(form)
        self.cpos = cpos.upper()

evanmiltenburg

Training a Dutch parser

Steps

1. Get the text data: wget http://kyoto.let.vu.nl/~miltenburg/public_data/wikicorpus/corpus/wikicorpus.txt.gz
2. Get the code for the structured n-grams: wget https://github.com/wlin12/wang2vec/archive/master.zip
3. Run unzip master.zip ; rm master.zip
4. Build the word vector code: Run cd wang2vec-master/ ; make ; cd ..
5. Train CBOW vectors: Run ./wang2vec-master/word2vec -train wikicorpus.txt -output cbow.vectors -type 0 -size 50 -window 5 -negative 10 -nce 0 -hs 0 -sample 1e-4 -threads 1 -iter 5 -cap 0 >> training.log 2>&1 &
6. Train Structured skipngram vectors: Run ./wang2vec-master/word2vec -train wikicorpus.txt -output structured_ngram.vectors -type 3 -size 50 -window 5 -negative 10 -nce 0 -hs 0 -sample 1e-4 -threads 1 -iter 5 -cap 0 >> training_ssg.log 2>&1 &