https://github.com/jugechengzi/rationalization-a2i
공식 코드Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets
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/julian-risch/JCDL2018
공식 코드https://github.com/julianyulu/icassp2021-mscnn-spu
공식 코드Efficient Speech Emotion Recognition Using Multi-Scale CNN and Attention
https://github.com/justinphan3110/SciFive
공식 코드SciFive: a text-to-text transformer model for biomedical literature
https://github.com/jvendrow/GuidedNMF
공식 코드https://github.com/jvking/bp-lda
공식 코드End-to-end Learning of LDA by Mirror-Descent Back Propagation over a Deep Architecture
https://github.com/jxhe/unify-parameter-efficient-tuning
공식 코드Towards a Unified View of Parameter-Efficient Transfer Learning
https://github.com/jyansir/text2tree
공식 코드https://github.com/k-rlange/lex2sent
공식 코드Lex2Sent: A bagging approach to unsupervised sentiment analysis
https://github.com/k-rlange/t2snarrativechanges
공식 코드Narrative Shift Detection: A Hybrid Approach of Dynamic Topic Models and Large Language Models
https://github.com/kaimihata/geo-bert
공식 코드On Geodesic Distances and Contextual Embedding Compression for Text Classification
https://github.com/kaiyin97/crsisllm
공식 코드https://github.com/kaize0409/HyperGAT
공식 코드Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
https://github.com/kakaobrain/irm-empirical-study
공식 코드https://github.com/kaleidophon/nlp-uncertainty-zoo
공식 코드https://github.com/kartikeypant/smokeng-tobacco-classification
공식 코드SmokEng: Towards Fine-grained Classification of Tobacco-related Social Media Text
https://github.com/karuna-bhaila/llm_unlearning
공식 코드https://github.com/katbailey/few-shot-text-classification
공식 코드Few-Shot Text Classification with Pre-Trained Word Embeddings and a Human in the Loop
https://github.com/kaylaschroeder/reliability
공식 코드https://github.com/kayoyin/interpret-lm
공식 코드https://github.com/kb-ding/ear
공식 코드A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning
https://github.com/kdavid2355/kopolitic-benchmark-dataset
공식 코드https://github.com/kddubey/pretrain-on-test
공식 코드https://github.com/keaml-jlu/mi-delight
공식 코드https://github.com/keaml-jlu/simstc
공식 코드A Simple Graph Contrastive Learning Framework for Short Text Classification
https://github.com/keremzaman/fusetoforget
공식 코드Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion
https://github.com/keyATM/keyATM
공식 코드https://github.com/kianaaa19/leopold
공식 코드https://github.com/kihansi95/linkmedia_attentionplausibilitybyconstraint
공식 코드Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation
https://github.com/kimjeyoung/plm_call
공식 코드Bag of Tricks for In-Distribution Calibration of Pretrained Transformers
https://github.com/kinit-sk/deni
공식 코드https://github.com/kinit-sk/l3d-sensitivity-investigation
공식 코드https://github.com/kinit-sk/semeval-2024-task-8-machine-text-detection
공식 코드KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detection
https://github.com/kiwi-lilo/amplify
공식 코드AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformer
https://github.com/kk7nc/HDLTex
공식 코드https://github.com/kk7nc/RMDL
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.