https://github.com/huggingface/transformers/blob/main/src/transformers/models/squeezebert/modeling_squeezebert.py
공식 코드SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
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/hugochan/KATE
공식 코드https://github.com/huiyegit/APLC_XLNet
공식 코드https://github.com/huiyegit/matchxml
공식 코드MatchXML: An Efficient Text-label Matching Framework for Extreme Multi-label Text Classification
https://github.com/huiying-li/blacklight
공식 코드Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks
https://github.com/huylb314/AVIAD_AVIJST
공식 코드Towards Autoencoding Variational Inference for Aspect-based Opinion Summary
https://github.com/hwang595/foe-iclr2024
공식 코드https://github.com/hyintell/topicx
공식 코드https://github.com/iQua/CVPR2020-Shoestring
공식 코드Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data
https://github.com/ibm/fastfit
공식 코드When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many Classes
https://github.com/ibm/intermediate-training-using-clustering
공식 코드Cluster & Tune: Boost Cold Start Performance in Text Classification
https://github.com/ibm/zero-shot-classification-boost-with-self-training
공식 코드https://github.com/iceboal/correlated-lda
공식 코드Fast, Flexible Models for Discovering Topic Correlation across Weakly-Related Collections
https://github.com/iclr-complex-order/complex-order
공식 코드https://github.com/idea-ccnl/fengshenbang-lm
공식 코드Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective
https://github.com/idiap/gile
공식 코드GILE: A Generalized Input-Label Embedding for Text Classification
https://github.com/idiap/mhan
공식 코드Multilingual Hierarchical Attention Networks for Document Classification
https://github.com/idirlab/claimspotter
공식 코드https://github.com/ielab/goldilocks-reproduce
공식 코드A Reproducibility Study of Goldilocks: Just-Right Tuning of BERT for TAR
https://github.com/iesl/leopard
공식 코드Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks
https://github.com/ifahim/toxic-preprocess
공식 코드Is preprocessing of text really worth your time for online comment classification?
https://github.com/iflytek/minirbt
공식 코드MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model
https://github.com/ignaciodeza/boq-classifier-icms
공식 코드https://github.com/ilhamfp/indonesian-text-classification-multilingual
공식 코드Improving Indonesian Text Classification Using Multilingual Language Model
https://github.com/iliaschalkidis/lmtc-eurlex57k
공식 코드Large-Scale Multi-Label Text Classification on EU Legislation
https://github.com/illdepence/cross-lingual-citations-from-en
공식 코드Cross-Lingual Citations in English Papers: A Large-Scale Analysis of Prevalence, Usage, and Impact
https://github.com/imperialite/BERT-Embeddings-For-ARA
공식 코드https://github.com/indobenchmark/indonlu
공식 코드IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding
https://github.com/inigo-jauregi/t3l
공식 코드T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification
https://github.com/inimah/protoinfomax
공식 코드ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection
https://github.com/ink-usc/bite
공식 코드BITE: Textual Backdoor Attacks with Iterative Trigger Injection
https://github.com/ink-usc/fewner
공식 코드Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
https://github.com/ink-usc/sparse-distillation
공식 코드Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models
https://github.com/inkiinki/mi-uap
공식 코드Interpreting Vulnerabilities of Multi-Instance Learning to Adversarial Perturbations
https://github.com/irenezihuili/hipool
공식 코드https://github.com/isarth/SemEval9_MIDAS
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.