Papers with Code 아카이브
Text Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 25
- 평가표
- 155
- 보존된 평가 기록
- 54
Text Generation is the task of generating text with the goal of appearing indistinguishable to human-written text. This task is more formally known as "natural language generation" in the literature.
Text generation can be addressed with Markov processes or deep generative models like LSTMs. Recently, some of the most advanced methods for text generation include BART, GPT and other GAN-based approaches. Text generation systems are evaluated either through human ratings or automatic evaluation metrics like METEOR, ROUGE, and BLEU.
Further readings:
<span style="color:grey; opacity: 0.6">( Image credit: Adversarial Ranking for Language Generation )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/jqk09a/CoRe-dialogue-filtering
공식 코드Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness
https://github.com/jsndg/emnlp23-llm-headline
공식 코드https://github.com/julianser/Ubuntu-Multiresolution-Tools
공식 코드Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
https://github.com/julianser/hred-latent-piecewise
공식 코드Piecewise Latent Variables for Neural Variational Text Processing
https://github.com/juliusc/pruning_mbr
공식 코드Faster Minimum Bayes Risk Decoding with Confidence-based Pruning
https://github.com/junewang0614/colarec
공식 코드Content-Based Collaborative Generation for Recommender Systems
https://github.com/jungokasai/beam_with_patience
공식 코드A Call for Clarity in Beam Search: How It Works and When It Stops
https://github.com/jungokasai/billboard
공식 코드Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand
https://github.com/jungokasai/twist_decoding
공식 코드https://github.com/junpliu/condigsum
공식 코드Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization
https://github.com/justinle4/diffusion
공식 코드https://github.com/justinlovelace/diffusion-guided-lm
공식 코드https://github.com/justinlovelace/latent-diffusion-for-language
공식 코드https://github.com/justinphan3110/CoTexT
공식 코드https://github.com/justinphan3110/SciFive
공식 코드SciFive: a text-to-text transformer model for biomedical literature
https://github.com/jvamvas/fastchrf
공식 코드Linear-time Minimum Bayes Risk Decoding with Reference Aggregation
https://github.com/jwaladhamala/BOLD-Bias-in-open-ended-language-generation
공식 코드BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
https://github.com/jxfeb/Generative_QA
공식 코드https://github.com/jxhe/sparse-text-prototype
공식 코드https://github.com/jxhe/vae-lagging-encoder
공식 코드Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
https://github.com/jy0205/lavit
공식 코드Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
https://github.com/jyonn/genre-requests
공식 코드ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models
https://github.com/jyonn/once
공식 코드ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models
https://github.com/k-amara/ConceptX
공식 코드Concept-Level Explainability for Auditing & Steering LLM Responses
https://github.com/k-amara/syntax-shap
공식 코드SyntaxShap: Syntax-aware Explainability Method for Text Generation
https://github.com/k2-fsa/ZipVoice
공식 코드ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
https://github.com/kaishxu/DFMed
공식 코드https://github.com/kaito25atugich/detector
공식 코드The Impact of Prompts on Zero-Shot Detection of AI-Generated Text
https://github.com/kaiyangwan/cogwriter
공식 코드A Cognitive Writing Perspective for Constrained Long-Form Text Generation
https://github.com/kakaobrain/magvlt
공식 코드https://github.com/kakaobrain/stg
공식 코드Selective Token Generation for Few-shot Natural Language Generation
https://github.com/kaleidophon/nlp-uncertainty-zoo
공식 코드https://github.com/kaleidophon/non-exchangeable-conformal-language-generation
공식 코드Non-Exchangeable Conformal Language Generation with Nearest Neighbors
https://github.com/kaniblu/hanja-sisg
공식 코드Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja
https://github.com/kaniblu/vhda
공식 코드Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.