paper-with-me

홈 › Papers

Universal Language Model Fine-Tuning with Subword Tokenization for Polish

2018-10-24 · Piotr Czapla, Jeremy Howard, Marcin Kardas

Universal Language Model for Fine-tuning [arXiv:1801.06146] (ULMFiT) is one of the first NLP methods for efficient inductive transfer learning. Unsupervised pretraining results in improvements on many NLP tasks for English. In this paper, we describe a new method that uses subword tokenization to adapt ULMFiT to languages with high inflection. Our approach results in a new state-of-the-art for the Polish language, taking first place in Task 3 of PolEval'18. After further training, our final model outperformed the second best model by 35%. We have open-sourced our pretrained models and code.

📄 PDF Abstract BibTeX arXiv:1810.10222

Code (2)

n-waves/poleval2018
simecek/Czech-ULMFiT

Tasks

Language ModelingLanguage ModellingTransfer Learning

Similar Papers 제목 키워드 기반

Can Perplexity Predict Fine-Tuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali

2024-04-28 · Nishant Luitel, Nirajan Bekoju, Anand Kumar Sah, Subarna Shakya

Recent language models use subwording mechanisms to handle Out-of-Vocabulary(OOV) words seen during test time and, their generation capacity is generally measured using perplexity, an intrinsic metric. It is known that i…

Language ModelingLanguage Modelling

MaxMatch-Dropout: Subword Regularization for WordPiece

2022-09-09 · COLING 2022 10 · Tatsuya Hiraoka

We present a subword regularization method for WordPiece, which uses a maximum matching algorithm for tokenization. The proposed method, MaxMatch-Dropout, randomly drops words in a search using the maximum matching algor…

Machine TranslationText ClassificationTranslation

Should we find another model?: Improving Neural Machine Translation Performance with ONE-Piece Tokenization Method without Model Modification

2021-06-01 · NAACL 2021 4 · Chanjun Park, Sugyeong Eo, Hyeonseok Moon, Heuiseok Lim

Most of the recent Natural Language Processing(NLP) studies are based on the Pretrain-Finetuning Approach (PFA), but in small and medium-sized enterprises or companies with insufficient hardware there are many limitation…

Machine TranslationmodelTranslation

BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages

2017-10-05 · LREC 2018 5 · Benjamin Heinzerling, Michael Strube

We present BPEmb, a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE). In an evaluation using fine-grained entity typing as testbed, BPEmb performs competitively, and f…

Entity TypingWord Embeddings

Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation

2026-04-29 · Théo Gigant, Bowen Peng, Jeffrey Quesnelle arxiv

Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work, we decouple the effect…