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/jingcheng-du/ML_Net-1
공식 코드ML-Net: multi-label classification of biomedical texts with deep neural networks
https://github.com/jingjing-nlp/knas
공식 코드https://github.com/jingqiangchen/concaps
공식 코드Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image Captioning
https://github.com/jitinkrishnan/Diversity-Based-Generalization
공식 코드Diversity-Based Generalization for Unsupervised Text Classification under Domain Shift
https://github.com/jitinkrishnan/transliteration-hindi-malayalam
공식 코드Cross-Lingual Text Classification of Transliterated Hindi and Malayalam
https://github.com/jixuan-wang/grad2task
공식 코드Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation
https://github.com/jiyfeng/disco4textcat
공식 코드https://github.com/jjacampos/FeedbackWeightedLearning
공식 코드https://github.com/jjzha/cal
공식 코드https://github.com/jkvc/modular-domain-adaptation
공식 코드https://github.com/jlee118/nprm
공식 코드https://github.com/jmraczynski/cer
공식 코드The Problem of Coherence in Natural Language Explanations of Recommendations
https://github.com/jmribeiro/dsl-project
공식 코드Pruning and Sparsemax Methods for Hierarchical Attention Networks
https://github.com/jmrludan/tbm
공식 코드Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck
https://github.com/jniimi/ensemble_inference
공식 코드A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification
https://github.com/jobpal/nex-cv
공식 코드https://github.com/joey1993/bert-defender
공식 코드Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification
https://github.com/johndmendonca/Ecoh
공식 코드ECoh: Turn-level Coherence Evaluation for Multilingual Dialogues
https://github.com/johndmendonca/maia-dqe
공식 코드Dialogue Quality and Emotion Annotations for Customer Support Conversations
https://github.com/johntailor/ft-topic
공식 코드https://github.com/joisino/wordtour
공식 코드Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem
https://github.com/jongwooko/musc
공식 코드Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks
https://github.com/jonrusert/sampleshielding
공식 코드https://github.com/jonrusert/suumcuique
공식 코드Suum Cuique: Studying Bias in Taboo Detection with a Community Perspective
https://github.com/jonrusert/vertattack
공식 코드VertAttack: Taking advantage of Text Classifiers' horizontal vision
https://github.com/jonzarecki/textual-membership-queries
공식 코드https://github.com/jonzarecki/textual-mqs
공식 코드https://github.com/jorgegus/autotext
공식 코드https://github.com/josh-rodriguez-csu/chunkingforllms
공식 코드Text Chunking for Document Classification for Urban System Management using Large Language Models
https://github.com/josipjukic/adapter-al
공식 코드Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings
https://github.com/jrmazarura/GPM
공식 코드https://github.com/js05212/BayesianDeepLearning-Survey
공식 코드https://github.com/jschuurmans/hsoftmax
공식 코드Global Hierarchical Neural Networks using Hierarchical Softmax
https://github.com/jslin/LARQS
공식 코드An Evaluation Dataset for Legal Word Embedding: A Case Study On Chinese Codex
https://github.com/jugechengzi/Rationalization-N2R
공식 코드Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.