500 papers with code • 38 benchmarks • 58 datasets
Text classification is the task of assigning a sentence or document an appropriate category. The categories depend on the chosen dataset and can range from topics.
( Image credit: Text Classification Algorithms: A Survey )
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.
Ranked #1 on Question Answering on CoQA
To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear.
Ranked #1 on Question Answering on Natural Questions (F1 (Long) metric)
Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting.
Ranked #13 on Sentiment Analysis on IMDb
With the success of language pretraining, it is highly desirable to develop more efficient architectures of good scalability that can exploit the abundant unlabeled data at a lower cost.
Ranked #6 on Reading Comprehension on RACE
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling.
Ranked #1 on Sentiment Analysis on Yelp Binary classification
Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch.
Ranked #3 on Text Classification on TREC-6