Unigram tokenization¶

!pip install datasets evaluate transformers[sentencepiece]

corpus = [
    "This is the Hugging Face course.",
    "This chapter is about tokenization.",
    "This section shows several tokenizer algorithms.",
    "Hopefully, you will be able to understand how they are trained and generate tokens.",
]

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("xlnet-base-cased")

from collections import defaultdict

word_freqs = defaultdict(int)
for text in corpus:
    words_with_offsets = tokenizer.backend_tokenizer.pre_tokenizer.pre_tokenize_str(text)
    new_words = [word for word, offset in words_with_offsets]
    for word in new_words:
        word_freqs[word] += 1

word_freqs

token_freqs = list(char_freqs.items()) + sorted_subwords[: 300 - len(char_freqs)]
token_freqs = {token: freq for token, freq in token_freqs}

from math import log

total_sum = sum([freq for token, freq in token_freqs.items()])
model = {token: -log(freq / total_sum) for token, freq in token_freqs.items()}

def encode_word(word, model):
    best_segmentations = [{"start": 0, "score": 1}] + [
        {"start": None, "score": None} for _ in range(len(word))
    ]
    for start_idx in range(len(word)):
        # This should be properly filled by the previous steps of the loop
        best_score_at_start = best_segmentations[start_idx]["score"]
        for end_idx in range(start_idx + 1, len(word) + 1):
            token = word[start_idx:end_idx]
            if token in model and best_score_at_start is not None:
                score = model[token] + best_score_at_start
                # If we have found a better segmentation ending at end_idx, we update
                if (
                    best_segmentations[end_idx]["score"] is None
                    or best_segmentations[end_idx]["score"] > score
                ):
                    best_segmentations[end_idx] = {"start": start_idx, "score": score}

    segmentation = best_segmentations[-1]
    if segmentation["score"] is None:
        # We did not find a tokenization of the word -> unknown
        return ["<unk>"], None

    score = segmentation["score"]
    start = segmentation["start"]
    end = len(word)
    tokens = []
    while start != 0:
        tokens.insert(0, word[start:end])
        next_start = best_segmentations[start]["start"]
        end = start
        start = next_start
    tokens.insert(0, word[start:end])
    return tokens, score

def compute_loss(model):
    loss = 0
    for word, freq in word_freqs.items():
        _, word_loss = encode_word(word, model)
        loss += freq * word_loss
    return loss

import copy


def compute_scores(model):
    scores = {}
    model_loss = compute_loss(model)
    for token, score in model.items():
        # We always keep tokens of length 1
        if len(token) == 1:
            continue
        model_without_token = copy.deepcopy(model)
        _ = model_without_token.pop(token)
        scores[token] = compute_loss(model_without_token) - model_loss
    return scores

percent_to_remove = 0.1
while len(model) > 100:
    scores = compute_scores(model)
    sorted_scores = sorted(scores.items(), key=lambda x: x[1])
    # Remove percent_to_remove tokens with the lowest scores.
    for i in range(int(len(model) * percent_to_remove)):
        _ = token_freqs.pop(sorted_scores[i][0])

    total_sum = sum([freq for token, freq in token_freqs.items()])
    model = {token: -log(freq / total_sum) for token, freq in token_freqs.items()}