paper-with-me

Papers

English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too

2020-05-26 · Asian Chapter of the Association for Computational Linguistics 2020 · Jason Phang, Iacer Calixto, Phu Mon Htut, Yada Pruksachatkun, Haokun Liu, Clara Vania, Katharina Kann, Samuel R. Bowman

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English settings. We investigate whether English intermediate-task training is still helpful on non-English target tasks. Using nine intermediate language-understanding tasks, we evaluate intermediate-task transfer in a zero-shot cross-lingual setting on the XTREME benchmark. We see large improvements from intermediate training on the BUCC and Tatoeba sentence retrieval tasks and moderate improvements on question-answering target tasks. MNLI, SQuAD and HellaSwag achieve the best overall results as intermediate tasks, while multi-task intermediate offers small additional improvements. Using our best intermediate-task models for each target task, we obtain a 5.4 point improvement over XLM-R Large on the XTREME benchmark, setting the state of the art as of June 2020. We also investigate continuing multilingual MLM during intermediate-task training and using machine-translated intermediate-task data, but neither consistently outperforms simply performing English intermediate-task training.

📄 PDF Abstract BibTeX arXiv:2005.13013

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual TransferHellaSwagQuestion AnsweringRetrievalSentenceSentence RetrievalXLM-RZero-Shot Cross-Lingual Transfer

Methods 이 논문이 사용한 방법론

XLM-R XLM-R

Similar Papers 제목 키워드 기반

English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too

2020-06-03 · Anonymous

Intermediate-task training has been shown to substantially improve pretrained model performance on many language understanding tasks, at least in monolingual English settings. Here, we investigate whether English interme…

Cross-Lingual TransferQuestion AnsweringXLM-RZero-Shot Cross-Lingual Transfer

Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking

2021-09-28 · EMNLP 2021 11 · Nikita Moghe, Mark Steedman, Alexandra Birch

Recent progress in task-oriented neural dialogue systems is largely focused on a handful of languages, as annotation of training data is tedious and expensive. Machine translation has been used to make systems multilingu…

Cross-Lingual TransferDialogue State TrackingMachine TranslationTransfer Learning

Sparse and Decorrelated Representations for Stable Zero-shot NMT

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Bokyung Son, Sungwon Lyu

Using a single encoder and decoder for all directions and training with English-centric data is a popular scheme for multilingual NMT. However, zero-shot translation under this scheme is vulnerable to changes in training…

DecoderNMTTranslation

Crosslingual Generalization through Multitask Finetuning

2022-11-03 · Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts 외

Multitask prompted finetuning (MTF) has been shown to help large language models generalize to new tasks in a zero-shot setting, but so far explorations of MTF have focused on English data and models. We apply MTF to the…

Coreference ResolutionCross-Lingual TransferQuestion AnsweringSentence Completion+2

Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Data

2023-06-06 · Janis Goldzycher, Moritz Preisig, Chantal Amrhein, Gerold Schneider

Most research on hate speech detection has focused on English where a sizeable amount of labeled training data is available. However, to expand hate speech detection into more languages, approaches that require minimal t…

Hate Speech DetectionNatural Language Inference