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/fornaciari/prosit
공식 코드ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholds
https://github.com/franciellevargas/FactNews
공식 코드Predicting Sentence-Level Factuality of News and Bias of Media Outlets
https://github.com/frederick0329/Wikipedia_title_dataset
공식 코드Learning Character-level Compositionality with Visual Features
https://github.com/fshp971/encoder-inference
공식 코드Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services
https://github.com/fskong/lh-mix
공식 코드LH-Mix: Local Hierarchy Correlation Guided Mixup over Hierarchical Prompt Tuning
https://github.com/fudanvi/benchmarking-chinese-text-recognition
공식 코드Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study
https://github.com/fywalter/label-bias
공식 코드https://github.com/fywalter/simptc
공식 코드https://github.com/gabrer/diatom
공식 코드A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User Reviews
https://github.com/gal-dmitry/HOLD_DETECTION_PUBLIC
공식 코드Text-Based Detection of On-Hold Scripts in Contact Center Calls
https://github.com/ganchengguang/SLG-framework
공식 코드https://github.com/ganchengguang/resume-IE-via-prompt
공식 코드A Few-shot Approach to Resume Information Extraction via Prompts
https://github.com/gatenlp/peft_fft_multilingual
공식 코드https://github.com/gchrysostomou/instance-specific-rationale
공식 코드https://github.com/gcunhase/StackedDeBERT
공식 코드Stacked DeBERT: All Attention in Incomplete Data for Text Classification
https://github.com/geobrain-ai/geogalactica
공식 코드GeoGalactica: A Scientific Large Language Model in Geoscience
https://github.com/georgehc/survival-topics
공식 코드https://github.com/georgeluimmortal/perplection_acl2023
공식 코드What Makes Pre-trained Language Models Better Zero-shot Learners?
https://github.com/getalp/Flaubert
공식 코드FlauBERT: Unsupervised Language Model Pre-training for French
https://github.com/ggcr/tinyemo
공식 코드TinyEmo: Scaling down Emotional Reasoning via Metric Projection
https://github.com/gguibon/protoseq
공식 코드Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks
https://github.com/ghazalmilani/one-shot-learning-from-text-iclp2023
공식 코드Towards One-Shot Learning for Text Classification using Inductive Logic Programming
https://github.com/ghazi-f/challenging-ssvaes
공식 코드Challenging the Semi-Supervised VAE Framework for Text Classification
https://github.com/ghomashudson/muld
공식 코드https://github.com/ghzhang233/Non-Discrimination-Learning-for-Text-Classification
공식 코드https://github.com/gianluigilopardo/anchors_text_theory
공식 코드A Sea of Words: An In-Depth Analysis of Anchors for Text Data
https://github.com/giannisnik/mpad
공식 코드Message Passing Attention Networks for Document Understanding
https://github.com/giannisnik/repset
공식 코드Rep the Set: Neural Networks for Learning Set Representations
https://github.com/gibranfp/SMH-Topic-Discovery
공식 코드Topic Discovery in Massive Text Corpora Based on Min-Hashing
https://github.com/gibranfp/Sampled-MinHashing
공식 코드Topic Discovery in Massive Text Corpora Based on Min-Hashing
https://github.com/gioannides/gaussian-adaptive-attention
공식 코드https://github.com/giseldo/neodataset
공식 코드https://github.com/giseldo/userstory
공식 코드https://github.com/gkaramanolakis/ISWD
공식 코드https://github.com/gkaramanolakis/clts
공식 코드Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.