Topic Classification
42 papers with code • 2 benchmarks • 7 datasets
Benchmarks
These leaderboards are used to track progress in Topic Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Datasets
Yahoo! Answers
How2Sign
KLUE
Taiga Corpus
Most implemented papers
Active learning in annotating micro-blogs dealing with e-reputation
This paper intends to develop a so-called active learning process for automatically annotating French language tweets that deal with the image (i. e., representation, web reputation) of politicians.
Hierarchical Transformers for Long Document Classification
helmy-elrais/RoBERT_Recurrence_over_BERT
•
•
BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm.
KLUE: Korean Language Understanding Evaluation
We introduce Korean Language Understanding Evaluation (KLUE) benchmark.
Cross-Lingual Adaptation using Structural Correspondence Learning
From these correspondences a cross-lingual representation is created that enables the transfer of classification knowledge from the source to the target language.
Controlling the Interaction Between Generation and Inference in Semi-Supervised Variational Autoencoders Using Importance Weighting
ghazi-f/SSPIWO
•
•
Even though Variational Autoencoders (VAEs) are widely used for semi-supervised learning, the reason why they work remains unclear.
Entailment as Few-Shot Learner
Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners.
Leveraging QA Datasets to Improve Generative Data Augmentation
The ability of generative language models (GLMs) to generate text has improved considerably in the last few years, enabling their use for generative data augmentation.
Topic-based Evaluation for Conversational Bots
knights207210/Deep-Learning-for-VUI
•
•
Dialog evaluation is a challenging problem, especially for non task-oriented dialogs where conversational success is not well-defined.
From Random to Supervised: A Novel Dropout Mechanism Integrated with Global Information
xusong19960424/global_cnn
•
•
CONLL 2018
Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training.
Topic Classification from Text Using Decision Tree, K-NN and Multinomial Naïve Bayes
One of the central motivations behind Natural Language Processing is detecting patterns.
