paper-with-me

홈 › Papers

2kenize: Tying Subword Sequences for Chinese Script Conversion

2020-05-07 · ACL 2020 6 · Pranav A, Isabelle Augenstein

Simplified Chinese to Traditional Chinese character conversion is a common preprocessing step in Chinese NLP. Despite this, current approaches have poor performance because they do not take into account that a simplified Chinese character can correspond to multiple traditional characters. Here, we propose a model that can disambiguate between mappings and convert between the two scripts. The model is based on subword segmentation, two language models, as well as a method for mapping between subword sequences. We further construct benchmark datasets for topic classification and script conversion. Our proposed method outperforms previous Chinese Character conversion approaches by 6 points in accuracy. These results are further confirmed in a downstream application, where 2kenize is used to convert pretraining dataset for topic classification. An error analysis reveals that our method's particular strengths are in dealing with code-mixing and named entities.

📄 PDF Abstract BibTeX arXiv:2005.03375

Code (1)

pranav-ust/2kenize 공식 구현

Tasks

General ClassificationTopic Classification

Similar Papers 제목 키워드 기반

Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet

2026-06-18 · Milan Miletić, Julie Kallini, Ekaterina Shutova arxiv

Multilingual language models often exhibit performance disparities across languages that can arise as early as the tokenization stage. Widely-used subword tokenization approaches favor high-resource languages, and tokeni…

SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing

2018-08-19 · EMNLP 2018 11 · Taku Kudo, John Richardson

This paper describes SentencePiece, a language-independent subword tokenizer and detokenizer designed for Neural-based text processing, including Neural Machine Translation. It provides open-source C++ and Python impleme…

Machine TranslationNMTSegmentationTranslation

How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese

2023-06-16 · Takuro Fujii, Koki Shibata, Atsuki Yamaguchi, Terufumi Morishita 외

This paper investigates the effect of tokenizers on the downstream performance of pretrained language models (PLMs) in scriptio continua languages where no explicit spaces exist between words, using Japanese as a case st…

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis

2026-07-25 · Poornima Kumaresan, Pavithra Muruganantham, Lakshmi Rajendran, Santhosh Sivasubramani arxiv

Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian lang…

Local Byte Fusion for Neural Machine Translation

2022-05-23 · Makesh Narsimhan Sreedhar, Xiangpeng Wan, Yu Cheng, Junjie Hu

Subword tokenization schemes are the dominant technique used in current NLP models. However, such schemes can be rigid and tokenizers built on one corpus do not adapt well to other parallel corpora. It has also been obse…

Cross-Lingual TransferDomain AdaptationMachine TranslationTranslation+1