mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer
Linting Xue,Noah Constant,Adam Roberts,Mihir Kale,Rami Al-Rfou,Aditya Siddhant,Aditya Barua,Colin Raffel +7 more
- pp 483-498
Reads0
Chats0
TLDR
This paper proposed a multilingual variant of T5, mT5, which was pre-trained on a new Common Crawl-based dataset covering 101 languages and achieved state-of-the-art performance on many multilingual benchmarks.Abstract:
The recent “Text-to-Text Transfer Transformer” (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages. We detail the design and modified training of mT5 and demonstrate its state-of-the-art performance on many multilingual benchmarks. We also describe a simple technique to prevent “accidental translation” in the zero-shot setting, where a generative model chooses to (partially) translate its prediction into the wrong language. All of the code and model checkpoints used in this work are publicly available.read more
Citations
More filters
Book ChapterDOI
Generating Abstractive Summaries of Lithuanian News Articles Using a Transformer Model
TL;DR: The authors train a monolingual transformer model on a large corpus of news articles and compare various output decoding algorithms for abstractive news summarization, achieving an average ROUGE-2 score 0.163.
Journal ArticleDOI
MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification
TL;DR: MaskEval is introduced, a reference-less metric for text summarization and simplification that is adapted to evaluate different quality dimensions by performing masked language modeling on the concatenation of the candidate and the source texts and features an attention-like weighting mechanism.
Journal ArticleDOI
Rethinking Semi-supervised Learning with Language Models
TL;DR: In this paper , the authors provide an extensive empirical study comparing five state-of-the-art self-training approaches and task-adaptive pre-training (TAPT) across various NLP tasks and data sizes, including in and out-ofdomain settings.
Proceedings ArticleDOI
MarSan at SemEval-2022 Task 6: iSarcasm Detection via T5 and Sequence Learners
Mary Najafi,Ehsan Tavan +1 more
TL;DR: A novel deep learning model on top of language models using an encoder module of the transformer, followed by LSTM and attention to utilizing past and future information, concentrating on informative tokens is proposed.
Journal ArticleDOI
NER2QUES: combining named entity recognition and sequence to sequence to automatically generating Vietnamese questions
Truong H. V. Phan,Phuc Do +1 more
TL;DR: The accuracy of the proposed NER2QUES method is more improved than previous methods’ accuracy and indicates that using NER to automatically generate questions may enrich question answering systems.
References
More filters
Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Posted Content
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Yinhan Liu,Myle Ott,Naman Goyal,Jingfei Du,Mandar Joshi,Danqi Chen,Omer Levy,Michael Lewis,Luke Zettlemoyer,Veselin Stoyanov +9 more
TL;DR: It is found that BERT was significantly undertrained, and can match or exceed the performance of every model published after it, and the best model achieves state-of-the-art results on GLUE, RACE and SQuAD.
Proceedings ArticleDOI
SQuAD: 100,000+ Questions for Machine Comprehension of Text
TL;DR: The Stanford Question Answering Dataset (SQuAD) as mentioned in this paper is a reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage.
Proceedings ArticleDOI
Unsupervised Cross-lingual Representation Learning at Scale
Alexis Conneau,Kartikay Khandelwal,Naman Goyal,Vishrav Chaudhary,Guillaume Wenzek,Francisco Guzmán,Edouard Grave,Myle Ott,Luke Zettlemoyer,Veselin Stoyanov +9 more
TL;DR: It is shown that pretraining multilingual language models at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks, and the possibility of multilingual modeling without sacrificing per-language performance is shown for the first time.
Proceedings ArticleDOI
Universal Language Model Fine-tuning for Text Classification
Jeremy Howard,Sebastian Ruder +1 more
TL;DR: Universal Language Model Fine-tuning (ULMFiT) as mentioned in this paper is an effective transfer learning method that can be applied to any task in NLP, and introduces techniques that are key for finetuning a language model.