Papers with Code 아카이브

Only Connect Walls Dataset Task 1 (Grouping)

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 1
보존된 평가 기록: 22

Split data into groups, taking into account knowledge in the form of constraints on points, groups of points, or clusters.

코드

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

https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/roberta/modeling.py

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/mpnet

MPNet: Masked and Permuted Pre-training for Language Understanding

https://github.com/PrashantRanjan09/Elmo-Tutorial

Deep contextualized word representations

https://github.com/PrashantRanjan09/WordEmbeddings-Elmo-Fasttext-Word2Vec

Deep contextualized word representations

https://github.com/RundongChou/elmo-chinese-oversimplified

Deep contextualized word representations

https://github.com/SindhuMadi/FakeNewsDetection

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/TEAMLAB-Lecture/deep_nlp_101

Deep contextualized word representations

https://github.com/Tencent/TurboTransformers

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/UKPLab/elmo-bilstm-cnn-crf

Deep contextualized word representations

https://github.com/UnknownGenie/altered-BERT-KPE

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/YC-wind/embedding_study

Deep contextualized word representations

https://github.com/abdumaa/hiqualprop

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/abhishekanand1710/noiseandbias

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/aistairc/kirt_bert_on_abci

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/allenai/bilm-tf

Deep contextualized word representations

https://github.com/allenai/scifact

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

https://github.com/ankurbanga/Language-Models

Deep contextualized word representations

https://github.com/askaydevs/distillbert-qa

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

https://github.com/awslabs/mlm-scoring

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/ayeffkay/rubert-tiny

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

https://github.com/bcaitech1/p2-klue-Heeseok-Jeong

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/benywon/ReCO

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/bestend/tf2-bi-lstm-crf-nni

Deep contextualized word representations

https://github.com/bfopengradient/NLP_ROBERTA

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/blawok/named-entity-recognition

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/bluejurand/Kaggle_QA_Google_Labeling

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/bplank/teaching-dl4nlp

Deep contextualized word representations

https://github.com/brightmart/roberta_zh

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/cheng18/bilm-tf

Deep contextualized word representations

https://github.com/clovaai/textual-kd-slu

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/common-english/bert-all

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/devhemza/BERTweet_sentiment_analysis

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/dig-team/hanna-benchmark-asg

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/dmlc/gluon-nlp

Deep contextualized word representations

https://github.com/dngback/co-forget-protocol

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

https://github.com/duanchi1230/NLP_Project_AI2_Reasoning_Challenge

RoBERTa: A Robustly Optimized BERT Pretraining Approach

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