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/etsurin/summaug
공식 코드Summarization-based Data Augmentation for Document Classification
https://github.com/eunseongc/mgfid
공식 코드https://github.com/evgeniael/predict_next_word
공식 코드Predict the Next Word: Humans exhibit uncertainty in this task and language models _____
https://github.com/ewoet/intrinsic-gender-probe
공식 코드How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification
https://github.com/expertailab/Is-BERT-self-attention-a-feature-selection-method
공식 코드Classifying Scientific Publications with BERT -- Is Self-Attention a Feature Selection Method?
https://github.com/extreme-bert/extreme-bert
공식 코드ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT
https://github.com/eyalbd2/PADA
공식 코드PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains
https://github.com/facebookresearch/LASER
공식 코드Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
https://github.com/facebookresearch/MLDoc
공식 코드A Corpus for Multilingual Document Classification in Eight Languages
https://github.com/facebookresearch/SentAugment
공식 코드Self-training Improves Pre-training for Natural Language Understanding
https://github.com/facebookresearch/SentEval
공식 코드What you can cram into a single vector: Probing sentence embeddings for linguistic properties
https://github.com/facebookresearch/StarSpace
공식 코드https://github.com/facebookresearch/fastText
공식 코드https://github.com/facebookresearch/parcus
공식 코드https://github.com/facebookresearch/randsent
공식 코드No Training Required: Exploring Random Encoders for Sentence Classification
https://github.com/facebookresearch/unirex
공식 코드UNIREX: A Unified Learning Framework for Language Model Rationale Extraction
https://github.com/facebookresearch/zest
공식 코드https://github.com/faisalqarah/saudibert
공식 코드SaudiBERT: A Large Language Model Pretrained on Saudi Dialect Corpora
https://github.com/fanioula/mlslcs
공식 코드Inducing Generalized Multi-Label Rules with Learning Classifier Systems
https://github.com/farahalshanik/qe
공식 코드Proactive Query Expansion for Streaming Data Using External Source
https://github.com/farhandhanani/mlmac
공식 코드https://github.com/fastai/fastai
공식 코드Universal Language Model Fine-tuning for Text Classification
https://github.com/finitearth/capo
공식 코드https://github.com/finitearth/promptolution
공식 코드https://github.com/fitz-like-coding/cwtm
공식 코드CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling
https://github.com/fjelenic/al-transfer
공식 코드On Dataset Transferability in Active Learning for Transformers
https://github.com/fjelenic/between-layer-ood
공식 코드Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
https://github.com/flair-iisc/watermark_tradeoffs
공식 코드https://github.com/flairnlp/fabricator
공식 코드Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs
https://github.com/flipz357/npc_gzip_exp
공식 코드https://github.com/flohauss/xmc_htc
공식 코드https://github.com/florex/xai-cnn-lrp
공식 코드https://github.com/fmplaza/zsl_nli_emotion_prompts
공식 코드Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora
https://github.com/fmtumbuka/relationembeddings
공식 코드Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction
https://github.com/forest-snow/alps
공식 코드Cold-start Active Learning through Self-supervised Language Modeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.