Text Classification
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.
Text Classification problems include emotion classification, news classification, citation intent classification, among others. Benchmark datasets for evaluating text classification capabilities include GLUE, AGNews, among others.
In recent years, deep learning techniques like XLNet and RoBERTa have attained some of the biggest performance jumps for text classification problems.
( Image credit: Text Classification Algorithms: A Survey )
Papers
Showing 1–10 of 3635 papers
All datasetsMTEBAG NewsDBpediaR8TREC-620NEWSUK Key Stage ReadabilityOhsumedYahoo! AnswersMRClimabenchNewsDiscourse
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Human (Post-Rec.) (Spangher et al., 2021) | macro F1 | 73.69 | — | Unverified |
| 2 | MT-Mac (Spangher et al., 2021) | macro F1 | 63.46 | — | Unverified |
| 3 | MT-Mic (Spangher et al., 2021) | macro F1 | 61.89 | — | Unverified |
| 4 | RL-IP/TT (Choubey et al., 2021) | macro F1 | 57 | — | Unverified |
| 5 | Document LSTM + Document encoding (Choubey et al., 2020) | macro F1 | 54.4 | — | Unverified |
| 6 | CRF Fine-grained (Choubey et al., 2020) | macro F1 | 52.9 | — | Unverified |
| 7 | Human (Blind) (Spangher et al., 2021) | macro F1 | 46.18 | — | Unverified |
| 8 | Feature-based (SVM) (Choubey et al., 2020) | macro F1 | 38.3 | — | Unverified |