SentencePieceTokenizer: charsmap entries that map to an empty string are not applied, so control characters become <unk>

Aberta
  • Algo errado?
#7,908 0 comentários 0 reações 0 responsáveis Ver no GitHub

Mantenedores costumam responder em até 1 dia

Ninguém assumiu esta issue ainda.

Avaliação

Dificuldade
3/5
Tempo estimado
1-2 dias
Facilidade para iniciantes
69/100
Tipo de issue
Bug
Clareza
Claramente especificada
Status de atividade
Ativa
Stack de tecnologia
csharp
Domínio
machine-learning

Direção de pesquisa

Start by locating SentencePieceTokenizer normalization and the charsmap handling used by both CreateFromTokenizerJson and the .model protobuf path. Reproduce the reported case with a\u0001b and compare the normalized output with SentencePiece; done means all listed code points mapped to an empty string are deleted and token IDs match the expected behavior.

Escrita pelo modelo de indexação a partir do texto da issue.

Descrição

area-Tokenizers untriaged

System Information:

  • OS & Version: Debian 13 (trixie), x64
  • ML.NET Version: Microsoft.ML.Tokenizers 3.0.0
  • .NET Version: .NET SDK 10.0.404

Describe the bug
The precompiled nmt_nfkc charsmap used by SentencePiece Unigram models maps 30 control characters to an empty string, i.e. the normalizer deletes them. SentencePieceTokenizer does not apply these entries: the character survives normalization and is encoded as <unk>. As a result, token IDs differ from both Hugging Face tokenizers and SentencePiece C++ on any text that contains these characters.

The affected code points are U+0001–U+0008, U+000B, U+000E–U+001F, U+007F, U+008F and U+009F.

To Reproduce
Model: intfloat/multilingual-e5-small, revision 614241f622f53c4eeff9890bdc4f31cfecc418b3, file onnx/tokenizer.json.

using Microsoft.ML.Tokenizers;

using var stream = File.OpenRead("tokenizer.json");
var tokenizer = SentencePieceTokenizer.CreateFromTokenizerJson(
    stream, addBeginningOfSentence: false, addEndOfSentence: false);

Console.WriteLine(string.Join(", ", tokenizer.EncodeToIds("a\u0001b")));
Console.WriteLine(string.Join(", ", tokenizer.EncodeToIds("hello\u007Fworld")));
Input Microsoft.ML.Tokenizers 3.0.0 Hugging Face tokenizers 0.23.3
"a\u0001b" [10, 3, 275] (▁a, <unk>, b) [1563] (▁ab)
"hello\u007Fworld" [33600, 31, 3, 32554] [33600, 31, 32554]

Expected behavior
Charsmap entries whose replacement is an empty string should delete the matched input, as SentencePiece and Hugging Face do.

Additional context
We ran every Unicode scalar value (1,112,063 code points) through the normalizer and compared the result with SentencePiece's own normalization. 1,112,033 match; all 30 differences are the code points listed above. Removing these characters before calling the tokenizer brings the result to 1,112,063 of 1,112,063. The behavior is the same whether the tokenizer is created from tokenizer.json or from the .model protobuf.

Workaround: strip the 30 code points before encoding.

A related tie-breaking difference is reported in #7909.

Linguagem predominante
C#
Estrelas
9.4k
Forks
2k
Merge médio
2d 18h
PRs com merge (30d)
64

Preparar o ambiente

Primeiros passos

  1. Leia a issue inteira e depois o guia de contribuição do projeto.
  2. Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
  3. Faça um fork do repositório e trabalhe em uma branch.
  4. Abra um pull request que referencie o número da issue.

Mais de dotnet/machinelearning

Todas as issues de dotnet/machinelearning

Issues semelhantes

Mais issues de C#

Receba novas issues na sua caixa de entrada

Um resumo curto de issues do GitHub para quem está começando.