https://github.com/nazya/kate
공식 코드Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
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/ncbi-nlp/BLUE_Benchmark
공식 코드https://github.com/ncbi-nlp/NCBI_BERT
공식 코드https://github.com/nd-hal/automated-ml-scoring-versus-generation
공식 코드https://github.com/nec-research/sensitivity-consistency-LLM
공식 코드What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering
https://github.com/nemesis1303/gfedntm
공식 코드https://github.com/nguyentthong/CLNTM
공식 코드https://github.com/nickyfot/emocommonsense
공식 코드VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning
https://github.com/nicomanzonelli/topic_model_attacks
공식 코드https://github.com/nisarahmedrana/arabicmlec
공식 코드https://github.com/niuwagege/LDRNet
공식 코드LDRNet: Enabling Real-time Document Localization on Mobile Devices
https://github.com/nlp-tlp/chatgpt-fmc
공식 코드Large Language Models for Failure Mode Classification: An Investigation
https://github.com/nlp4se/review-emotion-analysis
공식 코드What About Emotions? Guiding Fine-Grained Emotion Extraction from Mobile App Reviews
https://github.com/nlpaueb/multi-eurlex
공식 코드https://github.com/noise-learning/selfmix
공식 코드SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training
https://github.com/norahalshahrani/bert_synonym_attack
공식 코드Arabic Synonym BERT-based Adversarial Examples for Text Classification
https://github.com/novicestone/hyperminer
공식 코드https://github.com/nur-ag/emotion-classification
공식 코드https://github.com/nur-ag/emotion-ui
공식 코드https://github.com/nutcrtnk/dhgnet
공식 코드Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph
https://github.com/nyquixt/cascadetta
공식 코드Adaptive Cascading Network for Continual Test-Time Adaptation
https://github.com/oarriaga/face_classification
공식 코드Real-time Convolutional Neural Networks for Emotion and Gender Classification
https://github.com/oceanypt/CFd
공식 코드https://github.com/ogaloglu/pre-training-multilingual-document-encoders
공식 코드https://github.com/ogh/binclusion
공식 코드Leveraging Monolingual Data for Crosslingual Compositional Word Representations
https://github.com/oldaandozerskaya/age_based_classification
공식 코드A Comparative Study of Feature Types for Age-Based Text Classification
https://github.com/olexandryermilov/privacy-preserving-nlp
공식 코드Privacy- and Utility-Preserving NLP with Anonymized Data: A case study of Pseudonymization
https://github.com/omar-sharif03/NAACL-SRW-2021
공식 코드Emotion Classification in a Resource Constrained Language Using Transformer-based Approach
https://github.com/openXBOW/openXBOW
공식 코드openXBOW - Introducing the Passau Open-Source Crossmodal Bag-of-Words Toolkit
https://github.com/opennlplab/transnormer
공식 코드https://github.com/opinionchange2021/building-for-tomorrow
공식 코드Building for Tomorrow: Assessing the Temporal Persistence of Text Classifiers
https://github.com/orionw/multilingual-federated-learning
공식 코드https://github.com/oscarchew/dont-forget-your-language
공식 코드Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis
https://github.com/osu-cvl/learning-idk
공식 코드https://github.com/oughtinc/raft-baselines
공식 코드https://github.com/p-karisani/CEPC
공식 코드Multiple-Source Domain Adaptation via Coordinated Domain Encoders and Paired Classifiers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.