Papers with Code 아카이브

Cross-Lingual Transfer

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 1
보존된 평가 기록: 6

Cross-lingual transfer refers to transfer learning using data and models available for one language for which ample such resources are available (e.g., English) to solve tasks in another, commonly more low-resource, language.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/eric-ai-lab/pectvlm

공식 코드

Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment

https://github.com/ethahtz/multilingual_othello

공식 코드

mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?

https://github.com/ethanachi/multilingual-probing-visualization

공식 코드

Finding Universal Grammatical Relations in Multilingual BERT

https://github.com/facebookresearch/LASER

공식 코드

Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond

https://github.com/facebookresearch/XLM

공식 코드

Unsupervised Cross-lingual Representation Learning at Scale

https://github.com/facebookresearch/belebele

공식 코드

The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants

https://github.com/facebookresearch/cc_net

공식 코드

Unsupervised Cross-lingual Representation Learning at Scale

https://github.com/facebookresearch/contriever

공식 코드

Unsupervised Dense Information Retrieval with Contrastive Learning

https://github.com/fdschmidt93/free-lunch-xlt

공식 코드

Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging

https://github.com/fdschmidt93/ofa-xlt

공식 코드

One For All & All For One: Bypassing Hyperparameter Tuning with Model Averaging For Cross-Lingual Transfer

https://github.com/fe1ixxu/ZeroShot-CrossLing-Parsing

공식 코드

Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation

https://github.com/fe1ixxu/cd_id_mmt

공식 코드

Language-Aware Multilingual Machine Translation with Self-Supervised Learning

https://github.com/fe1ixxu/intra-distillation

공식 코드

The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains

https://github.com/fe1ixxu/mixed-gradient-few-shot

공식 코드

Por Qué Não Utiliser Alla Språk? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer

https://github.com/felipessalvatore/CLCD

공식 코드

A logical-based corpus for cross-lingual evaluation

https://github.com/ffaisal93/adapt_lang_phylogeny

공식 코드

Phylogeny-Inspired Adaptation of Multilingual Models to New Languages

https://github.com/ffaisal93/neg_inf

공식 코드

An Efficient Approach for Studying Cross-Lingual Transfer in Multilingual Language Models

https://github.com/fffffarmer/lsar

공식 코드

Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations

https://github.com/firatcekinel/fctr

공식 코드

Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish

https://github.com/for-ai/goodtriever

공식 코드

From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models

https://github.com/frankaging/oolong-crosslingual

공식 코드

Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies

https://github.com/fredxlpy/cross_lingual_prompt_tuning

공식 코드

Soft Prompt Tuning for Cross-Lingual Transfer: When Less is More

https://github.com/fredxlpy/crosslingualspaceimpactanalysis

공식 코드

Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space

https://github.com/gabriel819/zeroshot_ner

공식 코드

Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages

https://github.com/ghchen18/acl22-sixtp

공식 코드

Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation

https://github.com/ghchen18/emnlp2021-sixt

공식 코드

Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders

https://github.com/google-research/bleurt

공식 코드

Learning Compact Metrics for MT

https://github.com/google-research/byt5

공식 코드

ByT5: Towards a token-free future with pre-trained byte-to-byte models

https://github.com/google-research/multilingual-t5

공식 코드

mT5: A massively multilingual pre-trained text-to-text transformer

https://github.com/google-research/prompt-tuning

공식 코드

Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation

https://github.com/google-research/xtreme

공식 코드

XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization

https://github.com/gucci-j/lowres-cva

공식 코드

How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?

https://github.com/gucci-j/lowres-cve

공식 코드

How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?

https://github.com/hansd410/cross-lingfnd

공식 코드

Cross-lingual Transfer Learning for Fake News Detector in a Low-Resource Language

https://github.com/hanzhou032/xqa-dst

공식 코드

XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking

https://github.com/hassanmojab/metanli

공식 코드

Persian Natural Language Inference: A Meta-learning approach

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.