Text Classification On Trec 6

评估指标

Error

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
TM-Glove9.96Enhancing Interpretable Clauses Semantically using Pretrained Word Representation
byte mLSTM79.6A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors
DELTA (CNN)7.8DELTA: A DEep learning based Language Technology plAtform
SWEM-aver7.8Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
Capsule-B7.2Investigating Capsule Networks with Dynamic Routing for Text Classification
STM+TSED+PT+2L7.04The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning
GRU-RNN-GLOVE7.0All-but-the-Top: Simple and Effective Postprocessing for Word Representations
MPAD-path6.2Message Passing Attention Networks for Document Understanding
VLAWE5.8Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation
C-LSTM5.4A C-LSTM Neural Network for Text Classification
CoVe4.2Learned in Translation: Contextualized Word Vectors
CNN+MCFA4Translations as Additional Contexts for Sentence Classification
TBCNN4Discriminative Neural Sentence Modeling by Tree-Based Convolution-
LSTM-CNN3.9Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling
ULMFiT3.6Universal Language Model Fine-tuning for Text Classification
BERT-ITPT-FiT3.2How to Fine-Tune BERT for Text Classification?
RoBERTa+DualCL2.60Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation
USE_T+CNN1.93Universal Sentence Encoder
Automatic Label Error Correction0.40The Re-Label Method For Data-Centric Machine Learning
0 of 19 row(s) selected.
Text Classification On Trec 6 | SOTA | HyperAI超神经