https://github.com/pasinit/xlwic-runs
XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models
mT5: A massively multilingual pre-trained text-to-text transformer
mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
Unsupervised Dense Information Retrieval with Contrastive Learning
Simple and Effective Zero-shot Cross-lingual Phoneme Recognition
Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT
Unsupervised Dense Information Retrieval with Contrastive Learning
Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing
ByT5: Towards a token-free future with pre-trained byte-to-byte models
Unsupervised Dense Information Retrieval with Contrastive Learning
Rethinking embedding coupling in pre-trained language models
Rethinking embedding coupling in pre-trained language models
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
ByT5: Towards a token-free future with pre-trained byte-to-byte models
FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.