SentencePiece is a subword tokenizer and detokenizer for natural language processing. It performs subword segmentation, supporting the byte-pair-encoding (BPE) algorithm and unigram language model, and then converts this text into an id sequence guarantee perfect reproducibility of the normalization and subword segmentation.
Source: SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text ProcessingPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Language Modelling | 97 | 9.37% |
Question Answering | 60 | 5.80% |
Sentence | 46 | 4.44% |
Decoder | 43 | 4.15% |
Text Generation | 39 | 3.77% |
Translation | 31 | 3.00% |
Retrieval | 30 | 2.90% |
Machine Translation | 28 | 2.71% |
Natural Language Understanding | 20 | 1.93% |