Use Tensorflow and pre-trained FastText to get embeddings of unseen words

Question

I am using a pre-trained fasttext model https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md).

I use Gensim to load the fasttext model. It can output a vector for any words, no matter it is seen or unseen (out-of-vocabulary).

from gensim.models.wrappers import FastText
en_model = FastText.load_fasttext_format('../wiki.en/wiki.en')
print(en_model['car'])
print(en_model['carcaryou'])

In tensorflow, I know that I can use below code to get the trainable embeddings of seen words:

# Embedding layer
embeddings = tf.get_variable('embedding_matrix', [vocab_size, state_size], Trainable=True)
rnn_inputs = tf.nn.embedding_lookup(embeddings, x)

The indices of known words are easy to get. However, for those unseen words, FastText "predicts" their latent vectors based on sub-word patterns. Unseen words do not have any indices.

In this case, how should I use tensorflow to handle both known words and unseen words using fasttext?

Answer 1

I found a workaround using tf.py_func:

def lookup(arr):
    global model
    global decode

    decoded_arr = decode(arr)
    new_arr = np.zeros((*arr.shape, 300))
    for s, sent in enumerate(decoded_arr):
        for w, word in enumerate(sent):
            try:
                new_arr[s, w] = model.wv[word]
            except Exception as e:
                print(e)
                new_arr[s, w] = np.zeros(300)
    return new_arr.astype(np.float32)

z = tf.py_func(lookup, [x], tf.float32, stateful=True, name=None)

This piece of code works, (using French, sorry but does not matter)

import tensorflow as tf
import numpy as np
from gensim.models.wrappers import FastText

model = FastText.load_fasttext_format("../../Tracfin/dev/han/data/embeddings/cc.fr.300.bin")
decode = np.vectorize(lambda x: x.decode("utf-8"))

def lookup(arr):
    global model
    global decode

    decoded_arr = decode(arr)
    new_arr = np.zeros((*arr.shape, 300))
    for s, sent in enumerate(decoded_arr):
        for w, word in enumerate(sent):
            try:
                new_arr[s, w] = model.wv[word]
            except Exception as e:
                print(e)
                new_arr[s, w] = np.zeros(300)
    return new_arr.astype(np.float32)

def extract_words(token):
    # Split characters
    out = tf.string_split([token], delimiter=" ")
    # Convert to Dense tensor, filling with default value
    out = tf.reshape(tf.sparse_tensor_to_dense(out, default_value="<pad>"), [-1])
    return out


textfile = "text.txt"
words = [
    "ceci est un texte hexabromocyclododécanes intéressant qui mentionne des",
    "mots connus et des mots inconnus commeceluici ou celui-là polybromobiphényle",
]

with open(textfile, "w") as f:
    f.write("\n".join(words))

tf.reset_default_graph()
padded_shapes = tf.TensorShape([None])
padding_values = "<pad>"

dataset = tf.data.TextLineDataset(textfile)
dataset = dataset.map(extract_words, 2)
dataset = dataset.shuffle(10000, reshuffle_each_iteration=True)
dataset = dataset.repeat()
dataset = dataset.padded_batch(3, padded_shapes, padding_values)
iterator = tf.data.Iterator.from_structure(
    dataset.output_types, dataset.output_shapes
)
dataset_init_op = iterator.make_initializer(dataset, name="dataset_init_op")
x = iterator.get_next()
z = tf.py_func(lookup, [x], tf.float32, stateful=True, name=None)
sess = tf.InteractiveSession()
sess.run(dataset_init_op)
y, w = sess.run([x, z])
y = decode(y)

print(
    "\nWords out of vocabulary: ",
    np.sum(1 for word in y.reshape(-1) if word not in model.wv.vocab),
)
print("Lookup worked: ", all(model.wv[y[0][0][0]] == w[0][0][0]))

Prints:

Words out of vocabulary:  6
Lookup worked:  True

I did not try to optimize things, especially the lookup loop, comments are welcome