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/shehzaadzd/variational-classification
공식 코드https://github.com/shijie-wu/crosslingual-nlp
공식 코드Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT
https://github.com/shikarina/short_text_classification
공식 코드https://github.com/shininglab/cat
공식 코드Counterfactual Adversarial Learning with Representation Interpolation
https://github.com/shiningliang/Multi-level-Causality-Detection-Network
공식 코드A Multi-level Neural Network for Implicit Causality Detection in Web Texts
https://github.com/shizhediao/black-box-prompt-learning
공식 코드https://github.com/shjo-april/TTD
공식 코드TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
https://github.com/shmsw25/Channel-LM-Prompting
공식 코드Noisy Channel Language Model Prompting for Few-Shot Text Classification
https://github.com/shreydesai/adaptive-ensembling
공식 코드Adaptive Ensembling: Unsupervised Domain Adaptation for Political Document Analysis
https://github.com/shuaizhao95/Unlearning
공식 코드Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
https://github.com/shuningjin/discrete-text-rep
공식 코드Discrete Latent Variable Representations for Low-Resource Text Classification
https://github.com/shuzhouyuan/gnnavi
공식 코드GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network
https://github.com/shwinshaker/simseed
공식 코드https://github.com/sid-unizar/ling-int-survey
공식 코드Linguistic Interpretability of Transformer-based Language Models: a systematic review
https://github.com/siku-bert/sikugpt
공식 코드https://github.com/simonucl/HJCL
공식 코드https://github.com/simra-shahid/hyhtm
공식 코드https://github.com/singh-l/FNDLVS
공식 코드Fake News Detection: a comparison between available Deep Learning techniques in vector space
https://github.com/sinovation/ZEN
공식 코드ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
https://github.com/sjmeis/CSKE
공식 코드https://github.com/sjmeis/craml_beta
공식 코드Transforming Unstructured Text into Data with Context Rule Assisted Machine Learning (CRAML)
https://github.com/skoltech-nlp/formality
공식 코드Detecting Text Formality: A Study of Text Classification Approaches
https://github.com/skydustz/aec-domain-corpora
공식 코드Pretrained Domain-Specific Language Model for General Information Retrieval Tasks in the AEC Domain
https://github.com/skydustz/text-classification-based-approach-for-evaluating-and-enhancing-machine-interpretability-of-building
공식 코드https://github.com/slanglab/IndiaPoliceEvents
공식 코드https://github.com/sled-group/verifiable-coherent-nlu
공식 코드Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers
https://github.com/sleepthroughdifficulties/uapad
공식 코드On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection
https://github.com/slei109/tart
공식 코드TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation
https://github.com/smartcameras/selfcrossattn
공식 코드Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?
https://github.com/snowood1/BERT-ENN
공식 코드https://github.com/snsf-data/ml-peer-review-analysis
공식 코드A Supervised Machine Learning Approach for Assessing Grant Peer Review Reports
https://github.com/soberqian/TopicModel4J
공식 코드https://github.com/socialmediaie/pytail
공식 코드PyTAIL: Interactive and Incremental Learning of NLP Models with Human in the Loop for Online Data
https://github.com/sociovestix/lenu
공식 코드https://github.com/somethingx02/topical_wordvec_models
공식 코드A Neural Generative Model for Joint Learning Topics and Topic-Specific Word Embeddings
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.