View source for Word2vec basic.py

__NOTOC__
{|
|-
| Type: || Algolit extension
|-
| Datasets: || [[NearbySaussure|nearbySaussre]]
|-
| Technique: || [[word embeddings]]
|-
| Developed by: || a team of researchers led by Tomas Mikolov at Google, Claude Lévi-Strauss, Algolit
|}

This is an annotated version of the basic word2vec script. The code is based on [https://www.tensorflow.org/tutorials/word2vec this Word2Vec tutorial] provided by Tensorflow. 

==History==
Word2vec consists of related models used to generate vectors from words (also called [[word embeddings]]). It is a two-layer neural network, produced by a team of researchers led by [http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf Tomas Mikolov at Google]. The script that we use here is not the original version of word2vec. The original project is written in the programming language C, which made us look for a version of the script written in the programming language Python. Another Python implementation of word2vec is provided by [https://radimrehurek.com/gensim/models/word2vec.html Gensim].

==word2vec_basic_algolit.py==
[[File:Word-embeddings-steps-algoliterary-encounter.JPG|thumb|right|Each table is occupied with one of the multiple steps of the script word2vec_basic.py. Picture taken during the Algoliterary Encounter event in November 2017.]]

The structure of the annotated word2vec script is the following:

* Step 1: Download data.
* '''Algolit step 1''': read data from plain text file
** '''Algolit inspection''': wordlist.txt
* Step 2: Create a dictionary and replace rare words with UNK token.
** '''Algolit inspection''': counted.txt
** '''Algolit inspection''': dictionary.txt
** '''Algolit inspection''': data.txt
** '''Algolit inspection''': disregarded.txt
** '''Algolit adaption''': reversed-input.txt
* Step 3: Function to generate a training batch for the skip-gram model
* Step 4: Build and train a skip-gram model.
** '''Algolit inspection''': big-random-matrix.txt
** '''Algolit adaption''': select your own set of test words
* Step 5: Begin training.
** '''Algolit inspection''': training-words.txt
** '''Algolit inspection''': training-window-words.txt
** '''Algolit adaption''': visualisation of the cosine similarity calculation updates
** '''Algolit inspection''': logfile.txt
* Step 6: Visualize the embeddings.
** '''Algolit adaption''': select 3 words to be included in the graph

[[File:5 graphs nearbySaussure.png|thumb|right|Graph generated by the word2vec_basic.py Tensorflow tutorial, based on the [[NearbySaussure|nearbySaussre]] dataset.]]

===Source===
The script word2vec_basic.py provides an option to download a dataset from [http://mattmahoney.net/dc/text8.zip Matt Mahoney's home page]. It turns out to be a plain text document, without any punctuation or line breaks.

For the tests that we wanted to do with the script, we decided to work with an algoliterary dataset that circles around the structuralist linguistic theory of Ferdinand de Saussure: [[NearbySaussure|nearbySaussure]]. The dataset contains 424.811 words in total of which 24.651 words are unique.

Before we could use the three books that form this dataset as training material, we needed to remove all the punctuation from the file. To do this, we wrote a small python script [[text-punctuation-clean-up.py]]. The script saves a *stripped* version of the original book under another filename.

===wordlist.txt===
From continuous text to list of words, exported as wordlist.txt.

<pre>
[u'Introduction', u'saussure', u'today', u'Carol', u'sanders', u'Why', u'still', u'today', u'do', u'we', u'\ufb01nd', u'the', u'name', u'of', u'ferdinand', u'de', u'saussure', u'featuring', u'prominently', u'in', u'volumes', u'published', u'not', u'only', u'on', u'linguistics', u'but', u'on', u'a', u'multitude', u'of', u'topics',  ... ]
</pre>

===counted.txt===
From list of words to a list with the structure [(word, value)], exported as counted.txt.

<pre>
Counter({u'the': 22315, u'of': 16396, u'and': 8271, u'a': 8246, u'to': 7797, u'in': 7314, u'is': 5983, u'as': 4143, u'that': 3586, u'it': 2629, u'e': 2500, u'The': 2478, u's': 2332, u'language': 2281, u'saussure': 2201, u'which': 2101, u'by': 1962, u'this': 1944, u'on': 1937, u'be': 1808, u'or': 1751, u'r': 1713, u'not': 1689, u'an': 1680, ... })
</pre>

===dictionary.txt===
Reversed dictionary, a list of the 5000 (=vocabulary size) most common words, accompanied by an index number, exported as dictionary.txt.

<pre>
{0: 'UNK', 1: u'the', 2: u'of', 3: u'and', 4: u'a', 5: u'to', 6: u'in', 7: u'is', 8: u'as', 9: u'that', 10: u'it', 11: u'e', 12: u'The', 13: u's', 14: u'language', 15: u'saussure', 16: u'which', 17: u'by', 18: u'this', 19: u'on', 20: u'be', 21: u'or', 22: u'r', 23: u'not', 24: u'an', ... }
</pre>

===data.txt===
The object ''data'' is created, the original texts where words are replaced with index numbers, exported as data.txt.

<pre>
[1169, 15, 1289, 3020, 1427, 3697, 354, 1289, 269, 68, 1021, 1, 345, 2, 234, 34, 15, 4416, 0, 6, 3052, 293, 23, 64, 19, 31, 38, 19, 4, 0, 2, 3877, ... ]
</pre>

===disregarded.txt===
List of disregarded words, that fall outside the vocabulary size, exported as disregarded.txt.

<pre>
[u'prominently', u'multitude', u'Volumes', u'titles', u'lee', u'poynton', u'intriguing', u'Plastic', u'glasses', u'fathers', u'kronenfeld', u'Afresh', u'Impact', u'titles', u'excite', u'premature', u'\u2018course', u'Sole', u'brilliant', u'precocious', u'centuries', u'examines', u'tracing', u'barely', u'praise', ... ]
</pre>

===reversed-input.txt===
Reversed version of the initial dataset, where all the disregard words are replaced with ''UNK'' (unkown), exported as reversed-input.txt.

<pre>
Introduction saussure today Carol sanders Why still today do we ﬁnd the name of ferdinand de saussure featuring UNK in volumes published not only on linguistics but on a UNK of topics UNK with UNK such as culture and text discourse and methodology in Social research and cultural studies UNK and UNK 2000 or the UNK UNK UNK and church UNK UNK 1996 ...
</pre>

===big-random-matrix.txt===
A big random matrix is created, with a vector size of 5000x20, exported as big-random-matrix.txt.

<pre>
 [[  7.91555882e-01   4.78600025e-01  -7.13676214e-01   2.30826855e-01
    6.61124229e-01   2.52689123e-01   6.37347698e-02   2.63915062e-01
    7.84061432e-01   6.69055700e-01   3.71650457e-01  -3.47790241e-01
   -4.34857845e-01  -9.00017262e-01   5.75044394e-01  -2.66819954e-01
    2.29521990e-01  -1.87541008e-01   7.47018099e-01  -8.54661465e-01]
 [  1.86723471e-01  -5.84969044e-01  -7.00650215e-01   7.50902653e-01
    2.52289057e-01  -9.68446016e-01  -1.12547159e-01  -9.01058912e-01
   -5.95885992e-01   3.08442831e-01   3.84899616e-01   7.09214926e-01
    9.58799362e-01  -8.78485441e-01  -3.27231169e-01   6.92137718e-01
    8.31190109e-01   1.67458773e-01   2.05923319e-01  -8.14627409e-01]
 [ -6.24799252e-01   9.01598454e-01   7.46447325e-01   5.45922041e-01
    4.28986549e-02  -2.75697231e-01   5.12938023e-01  -4.38443661e-01
    7.13398457e-01  -9.77021456e-01  -6.00349426e-01  -1.46302462e-01
   -9.75251198e-02  -1.80129766e-01   4.47291374e-01  -9.00330782e-01
    8.20701122e-02   9.37094688e-01  -8.20110321e-01  -7.58672953e-01] ... ]
</pre>

===training-words.txt===
Export a training batch of 64 words, with a vector size of 128x20, exported as training-words.txt.

<pre>
[ 323  323   52   52  107  107 2984 2984    3    3 1092 1092   48   48    4
    4    0    0 2898 2898   89   89   66   66   20   20   28   28    0    0
    4    4    0    0  142  142   28   28    0    0    0    0  173  173  697
  697 1054 1054  133  133    0    0    0    0   13   13 4364 4364 1146 1146
    2    2    1    1  201  201    2    2 1432 1432   26   26   12   12  201
  201    2    2  219  219    5    5  813  813  290  290    0    0 3071 3071
    5    5    1    1  280  280 2485 2485  705  705    6    6  144  144   28
   28    4    4 1125 1125    2    2  301  301    9    9    7    7 2851 2851
    6    6   16   16    0    0 3574 3574]
</pre>

Or in words: 

<pre>
['One', 'One', 'can', 'can', 'then', 'then', 'enter', 'enter', 'and', 'and', 'remain', 'remain', 'In', 'In', 'a', 'a', 'UNK', 'UNK', 'synchronics', 'synchronics', 'This', 'This', 'would', 'would', 'be', 'be', 'for', 'for', 'UNK', 'UNK', 'a', 'a', 'UNK', 'UNK', 'distinction', 'distinction', 'for', 'for', 'UNK', 'UNK', 'UNK', 'UNK', 'historical', 'historical', 'questions', 'questions', 'somewhat', 'somewhat', 'like', 'like', 'UNK', 'UNK', 'UNK', 'UNK', 's', 's', 'separating', 'separating', 'off', 'off', 'of', 'of', 'the', 'the', 'book', 'book', 'of', 'of', 'god', 'god', 'from', 'from', 'The', 'The', 'book', 'book', 'of', 'of', 'nature', 'nature', 'to', 'to', 'give', 'give', 'himself', 'himself', 'UNK', 'UNK', 'Access', 'Access', 'to', 'to', 'the', 'the', 'latter', 'latter', 'eagleton', 'eagleton', 'argues', 'argues', 'in', 'in', 'fact', 'fact', 'for', 'for', 'a', 'a', 'Process', 'Process', 'of', 'of', 'reading', 'reading', 'that', 'that', 'is', 'is', 'dialectical', 'dialectical', 'in', 'in', 'which', 'which', 'UNK', 'UNK', 'undergo', 'undergo']
</pre>

===training-window-words.txt===
Export a the 128 connected window words, one to the left, one to the right, with a vector size of 128x20, exported as training-window-words.txt.

<pre>
[[0] [52] [107] [323] [2984] [52] [3] [107] [1092] [2984] [48] [3] [4] [1092] [48] [0] [2898] [4] [89] [0] [66] [2898] [20] [89] [66] [28] [20] [0] [28] [4] [0] [0] [4] [142] [28] [0] [142] [0] [28] [0] [173] [0] [0] [697] [1054] [173] [697] [133] [0] [1054] [133] [0] [0] [13] [4364] [0] [13] [1146] [4364] [2] [1146] [1] [201] [2] [1] [2] [1432] [201] [26] [2] [1432] [12] [26] [201] [12] [2] [219] [201] [5] [2] [813] [219] [290] [5] [0] [813] [290] [3071] [5] [0] [1] [3071] [5] [280] [2485] [1] [705] [280] [6] [2485] [144] [705] [28] [6] [4] [144] [1125] [28] [2] [4] [1125] [301] [9] [2] [7] [301] [9] [2851] [6] [7] [2851] [16] [0] [6] [3574] [16] [0] [4331]]
</pre>

<br>Or in words: 

<pre>
['UNK', 'can', 'then', 'One', 'enter', 'can', 'and', 'then', 'remain', 'enter', 'In', 'and', 'a', 'remain', 'In', 'UNK', 'synchronics', 'a', 'This', 'UNK', 'would', 'synchronics', 'be', 'This', 'would', 'for', 'be', 'UNK', 'for', 'a', 'UNK', 'UNK', 'a', 'distinction', 'for', 'UNK', 'distinction', 'UNK', 'for', 'UNK', 'historical', 'UNK', 'UNK', 'questions', 'somewhat', 'historical', 'questions', 'like', 'UNK', 'somewhat', 'like', 'UNK', 'UNK', 's', 'separating', 'UNK', 's', 'off', 'separating', 'of', 'off', 'the', 'book', 'of', 'the', 'of', 'god', 'book', 'from', 'of', 'god', 'The', 'from', 'book', 'The', 'of', 'nature', 'book', 'to', 'of', 'give', 'nature', 'himself', 'to', 'UNK', 'give', 'himself', 'Access', 'to', 'UNK', 'the', 'Access', 'to', 'latter', 'eagleton', 'the', 'argues', 'latter', 'in', 'eagleton', 'fact', 'argues', 'for', 'in', 'a', 'fact', 'Process', 'for', 'of', 'a', 'Process', 'reading', 'that', 'of', 'is', 'reading', 'that', 'dialectical', 'in', 'is', 'dialectical', 'which', 'UNK', 'in', 'undergo', 'which', 'UNK', 'revision']
</pre>

===logfile.txt===
Save training log, exported as logfile.txt.

<pre>
step: 60000
loss value: 5.90600517762
Nearest to human: physical, grammatical, empirical, social, Human, real, Linguistic, universal, Lacan, Public,
Nearest to system: System, theory, category, phenomenon, state, center, systems, collection, Psychology, Analogy,

step: 62000
loss value: 5.81202450609
Nearest to human: social, signifying, linguistic, coherent, universal, rationality, mental, empirical, Linguistic, grammatical,
Nearest to system: state, structure, unit, consciousness, System, expression, center, phenomena, category, phenomenon,

step: 64000
loss value: 5.75922590137
Nearest to human: author, grammatical, Human, Public, physical, normative, ego, Sign, linguistic, arbitrary,
Nearest to system: System, metaphysics, changes, state, systems, knowledge, listener, unit, Understanding, language,
</pre>

[[Category:Algoliterary-Encounters]]