SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing (D18-2)
Copied to clipboard
| Challenge: | Existing subword segmentation tools assume input is pre-tokenized into word sequences, but SentencePiece can train subword models directly from raw sentences. |
| Approach: | They propose a language-independent subword tokenizer and detokenizer for Neural-based text processing. |
| Outcome: | The proposed system achieves comparable accuracy to training from raw sentences. |
Similar Papers
Bilingual Subword Segmentation for Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing subword segmentation methods tokenize sentences without considering translation . proposed method could be more favorable to machine translation if it uses bilingual sentences . |
| Approach: | They propose a subword segmentation method that tokenizes sentences by using subword units induced from bilingual sentences. |
| Outcome: | The proposed method improves translation performance on translation tasks up to +0.81 BLEU. |
Neural Machine Translation without Embeddings (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing models operate over subword tokens, but byte-based models employ a different approach . a one-hot representation of each byte does not hurt performance, but it improves BLEU scores . |
| Approach: | They propose to represent every computerized text as a sequence of bytes via UTF-8 . this eliminates the need for an embedding layer and improves performance . |
| Outcome: | The proposed model improves BLEU scores on byte-to-byte translation models compared to character-level models . the proposed model does not require an embedding layer and does not drop out of the decoder . |
MaxMatch-Dropout: Subword Regularization for WordPiece (2022.coling-1)
Copied to clipboard
| Challenge: | Existing subword regularization methods are specialized to a particular tokenizer type. |
| Approach: | They propose a subword regularization method for WordPiece that uses a maximum matching algorithm for tokenization. |
| Outcome: | The proposed method improves the performance of text classification and machine translation tasks as well as other subword regularization methods. |
How Important Is Tokenization in French Medical Masked Language Models? (2024.lrec-main)
Copied to clipboard
| Challenge: | Word tokenization into subword units has become the prevailing standard in the field of natural language processing (NLP) over recent years . the precise factors contributing to its success remain unclear . |
| Approach: | They propose a tokenization strategy that integrates morpheme-enriched word segmentation into existing tokenization methods. |
| Outcome: | The proposed tokenization strategy outperforms character and word tokenization but the precise factors contributing to its success remain unclear. |
Local Byte Fusion for Neural Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing NLP models rely on a pre-built subword tokenizer to tokenize a sentence . this can be rigid and subwords from low-resource languages are under-represented . |
| Approach: | They propose a method for byte-based machine translation that aggregates local semantic information. |
| Outcome: | The proposed method improves on multilingual translation and cross-lingual transfer . it is parameter-efficient and performs competitively to subword models, it is shown . |
Fast WordPiece Tokenization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for tokenization of text are not efficient, but they are based on Aho-Corasick's algorithm. |
| Approach: | They propose an efficient algorithm for WordPiece tokenization using a longest-match-first strategy . they propose an algorithm whose tokenization complexity is strictly O(n) |
| Outcome: | The proposed method is 8.2x faster than HuggingFace Tokenizers and 5.1x faster on average for general text tokenization. |
Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates (P18-1)
Copied to clipboard
| Challenge: | Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation. |
| Approach: | They propose a method to regularize subword segmentations probabilistically by sampling subwords . they also propose 'unigram' language model to be used for better subword sampling . |
| Outcome: | The proposed method improves on low resource and out-of-domain settings with multiple corpora. |
Treepiece: Faster Semantic Parsing via Tree Tokenization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Autoregressive (AR) encoder-decoder neural networks are slow in sequential prediction of natural language to machine-readable parse trees. |
| Approach: | They propose a technique that tokenizes a parse tree into subtrees and generates one subtrea per decoding step. |
| Outcome: | The proposed approach shows 4.6 times faster decoding speed and comparable speed but significantly higher accuracy compared to non-autoregressive (NAR) models. |
CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Currently, there is no dataset containing compound and non-compound words across languages . however, current LLMs perform poorly on words tokenized unfavorably by subword tokenization. |
| Approach: | They propose to use a Wiktionary dataset to evaluate large language models on decompounding . they find that current LLMs perform poorly on words tokenized unfavorably . |
| Outcome: | The proposed model outperforms the best unsupervised models by 13.9% accuracy on average. |
Should we find another model?: Improving Neural Machine Translation Performance with ONE-Piece Tokenization Method without Model Modification (2021.naacl-industry)
Copied to clipboard
| Challenge: | Recent studies using pretrain-finetuning approach have achieved state-of-the-art (SOTA) performance in many natural language processing tasks. |
| Approach: | They propose a new tokenization method that combines morphology-considered subword tokenization and vocabulary methods to address this limitation. |
| Outcome: | The proposed method can be used without modifying the model structure. |