Papers with Code 아카이브
Cross-Lingual
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 0
- 보존된 평가 기록
- 0
Cross-lingual natural language processing is the task of 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/Beacontownfc/rembert_paddle
Rethinking embedding coupling in pre-trained language models
https://github.com/BramVanroy/astred
Word Alignment by Fine-tuning Embeddings on Parallel Corpora
https://github.com/BunsenFeng/M-AbstainQA
The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
https://github.com/D-Roberts/multilingual-nli-ECIR2021
https://github.com/DevSinghSachan/unsupervised-passage-reranking
Unsupervised Dense Information Retrieval with Contrastive Learning
https://github.com/JoungheeKim/Non-Attentive-Tacotron
K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables
https://github.com/JunjieHu/xtreme-dev
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
https://github.com/Katherinaxxx/Paper-ReadingNotes
Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer
https://github.com/KoshiroSato/Flask_NLP_App
mT5: A massively multilingual pre-trained text-to-text transformer
https://github.com/KoshiroSato/Simple_Transformers_mT5_finetuning
mT5: A massively multilingual pre-trained text-to-text transformer
https://github.com/KyGao/token-level-classification
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
https://github.com/LawrenceDuan/myLASER
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
https://github.com/Mind23-2/MindCode-151
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
https://github.com/MindCode-4/code-13/tree/main/TSGD
https://github.com/MindCode-4/code-5/tree/main/xlm_roberta_xl
https://github.com/MindSpore-scientific-2/code-3/tree/main/TSGD
https://github.com/MindSpore-scientific/code-12/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions
https://github.com/MindSpore-scientific/code-14/tree/main/TSGD
https://github.com/MorenoLaQuatra/bart-it
mT5: A massively multilingual pre-trained text-to-text transformer
https://github.com/PaddlePaddle/FleetX/blob/develop/examples/resnet/train_fleet_sharding.py
ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/rembert
Rethinking embedding coupling in pre-trained language models
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-m
https://github.com/ScandEval/ScandEval
ScandEval: A Benchmark for Scandinavian Natural Language Processing
https://github.com/Stanley-Zheng/ignitionhacks
https://github.com/TheophileBlard/french-sentiment-analysis-with-bert
MultiFiT: Efficient Multi-lingual Language Model Fine-tuning
https://github.com/Tikquuss/meta_XLM
https://github.com/Tony4469/laser-agir
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
https://github.com/Unbabel/COMET
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
https://github.com/UniversalNER/uner_code
Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark
https://github.com/YuweiYin/HLT-MT
https://github.com/aaronsom/wmt21-qe-tudarmstadt
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer
https://github.com/ajd12342/inflection-pytorch
https://github.com/aleksac99/SQuAD-SR
https://github.com/amazon-research/stil-mbart-multiatis
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
https://github.com/amazon-science/multiatis
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.