Papers with Code 아카이브
Text Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 16
- 평가표
- 101
- 보존된 평가 기록
- 341
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.
<span style="color:grey; opacity: 0.6">( Image credit: Text Classification Algorithms: A Survey )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/csinva/imodelsX
공식 코드https://github.com/cuteythyme/q-diversity
공식 코드Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
https://github.com/cvangysel/SERT
공식 코드https://github.com/cvejoski/Neural-Dynamic-Focused-Topic-Model
공식 코드https://github.com/cyclicalcurriculum/cyclical-curriculum
공식 코드https://github.com/cyx617/Text-Classification-MSFF-QDConv-Model
공식 코드Multi-Scale Feature Fusion Quantum Depthwise Convolutional Neural Networks for Text Classification
https://github.com/dahyun-kang/lazygrounding
공식 코드In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation
https://github.com/daiquocnguyen/QGNN
공식 코드https://github.com/daiquocnguyen/gnn-regvd
공식 코드ReGVD: Revisiting Graph Neural Networks for Vulnerability Detection
https://github.com/dair-iitd/PoolingAnalysis
공식 코드Why and when should you pool? Analyzing Pooling in Recurrent Architectures
https://github.com/daisean/hint
공식 코드Hierarchical information matters: Text classification via tree based graph neural network
https://github.com/daisean/tent
공식 코드Hierarchical information matters: Text classification via tree based graph neural network
https://github.com/daiyongya/markbert
공식 코드https://github.com/dallal9/bibrank
공식 코드BibRank: Automatic Keyphrase Extraction Platform Using~Metadata
https://github.com/dallascard/neural_topic_models
공식 코드https://github.com/dallascard/scholar
공식 코드https://github.com/damithdr/legal-classification
공식 코드Can Model Fusing Help Transformers in Long Document Classification? An Empirical Study
https://github.com/damo-nlp-sg/sstuning
공식 코드https://github.com/danishpruthi/evaluating-explanations
공식 코드Evaluating Explanations: How much do explanations from the teacher aid students?
https://github.com/dao-ailab/flash-attention
공식 코드FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
https://github.com/dasol-choi/komultitext
공식 코드https://github.com/data-lang/text-summarization-sota-experiment
공식 코드Survey on Abstractive Text Summarization: Dataset, Models, and Metrics
https://github.com/dathong/ProtoryNet
공식 코드ProtoryNet - Interpretable Text Classification Via Prototype Trajectories
https://github.com/datquocnguyen/jLDADMM
공식 코드https://github.com/davialvb/intent-citation-network
공식 코드Leveraging GANs for citation intent classification and its impact on citation network analysis
https://github.com/david-yoon/attentive-modality-hopping-for-SER
공식 코드Attentive Modality Hopping Mechanism for Speech Emotion Recognition
https://github.com/davidtw999/bemps
공식 코드Diversity Enhanced Active Learning with Strictly Proper Scoring Rules
https://github.com/dbmdz/berts
공식 코드https://github.com/ddangelov/Top2Vec
공식 코드https://github.com/ddhruvkr/contradoc
공식 코드ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models
https://github.com/ddnas/ddnas
공식 코드DDNAS: Discretized Differentiable Neural Architecture Search for Text Classification
https://github.com/decile-team/spear
공식 코드https://github.com/declare-lab/doublemix
공식 코드DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification
https://github.com/declare-lab/identifiable-transformers
공식 코드More Identifiable yet Equally Performant Transformers for Text Classification
https://github.com/declare-lab/sat
공식 코드SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.