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/cheng-li/pyramid
공식 코드Regularizing Model Complexity and Label Structure for Multi-Label Text Classification
https://github.com/chengq220/Facial_Perturb
공식 코드https://github.com/chenxran/ok-transformer
공식 코드Enhancing Natural Language Representation with Large-Scale Out-of-Domain Commonsense
https://github.com/chenyangh/SemEval2019Task3
공식 코드https://github.com/chesterdu/contrastive_summary
공식 코드Constructing Contrastive samples via Summarization for Text Classification with limited annotations
https://github.com/chrisisking/zero-shot-text-classification
공식 코드Label Agnostic Pre-training for Zero-shot Text Classification
https://github.com/christoschr97/misinf-detection-llms
공식 코드Identifying Misinformation on YouTube through Transcript Contextual Analysis with Transformer Models
https://github.com/christospi/glc-nllp-21
공식 코드Multi-granular Legal Topic Classification on Greek Legislation
https://github.com/chschroeder/self-training-for-sample-efficient-active-learning
공식 코드https://github.com/chtmp223/topicgpt
공식 코드https://github.com/chuge0335/pc-cot
공식 코드https://github.com/chunliu-cs/llmembed-acl2024
공식 코드LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification
https://github.com/cimm-kzn/RuDReC
공식 코드https://github.com/cisnlp/colexificationnet
공식 코드https://github.com/cisnlp/taxi1500
공식 코드Taxi1500: A Multilingual Dataset for Text Classification in 1500 Languages
https://github.com/cisnlp/xampler
공식 코드XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples
https://github.com/climabench/climabench
공식 코드Towards Answering Climate Questionnaires from Unstructured Climate Reports
https://github.com/climatebert/language-model
공식 코드ClimateBert: A Pretrained Language Model for Climate-Related Text
https://github.com/clinc/oos-eval
공식 코드An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
https://github.com/clintpgeorge/clda
공식 코드Analyses of Multi-collection Corpora via Compound Topic Modeling
https://github.com/clips/interpret_with_rules
공식 코드https://github.com/clovaai/length-adaptive-transformer
공식 코드Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
https://github.com/clovaai/ssmix
공식 코드https://github.com/clovaai/vat-d
공식 코드Consistency Training with Virtual Adversarial Discrete Perturbation
https://github.com/coastalcph/lw-robust
공식 코드https://github.com/coastalcph/multi-label-classification-t5
공식 코드https://github.com/coastalcph/trldc
공식 코드Revisiting Transformer-based Models for Long Document Classification
https://github.com/constantinouchristos/ood-ahm
공식 코드Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification
https://github.com/constraint-solvers/benchmark-corruptions
공식 코드Benchmarking Popular Classification Models' Robustness to Random and Targeted Corruptions
https://github.com/copenlu/xai-benchmark
공식 코드A Diagnostic Study of Explainability Techniques for Text Classification
https://github.com/cosmoquester/memoria
공식 코드Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture
https://github.com/coswindywang/HdLM
공식 코드Making Language Model a Hierarchical Classifier and Generator
https://github.com/crazyofapple/at-bmc
공식 코드Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction
https://github.com/createmomo/instance-level-reliability
공식 코드Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks
https://github.com/csebuetnlp/banglabert
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.