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/rsabilio/nereval-braziliancorporatetranscriptions
공식 코드https://github.com/rsabilio/nereval-braziliancorporatetranscripts
공식 코드https://github.com/rsvp-ai/semantic_unwritten
공식 코드https://github.com/rtaori/data_feedback
공식 코드Data Feedback Loops: Model-driven Amplification of Dataset Biases
https://github.com/rucaibox/awesome-text-diffusion-models
공식 코드Diffusion Models for Non-autoregressive Text Generation: A Survey
https://github.com/rucaibox/context-tuning
공식 코드Context-Tuning: Learning Contextualized Prompts for Natural Language Generation
https://github.com/rucaibox/div-ref
공식 코드Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References
https://github.com/rucaibox/elmer
공식 코드ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generation
https://github.com/rucaibox/live
공식 코드Learning to Imagine: Visually-Augmented Natural Language Generation
https://github.com/rucaibox/mvp
공식 코드MVP: Multi-task Supervised Pre-training for Natural Language Generation
https://github.com/rucaibox/para-ref
공식 코드Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References
https://github.com/rucaibox/transfer-prompts-for-text-generation
공식 코드https://github.com/rucaibox/unicrs
공식 코드Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning
https://github.com/rucaibox/wsdm2022-c2crs
공식 코드C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender System
https://github.com/ruckbreasoning/glm-dialog
공식 코드GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation
https://github.com/ruinunca/PGTask
공식 코드PGTask: Introducing the Task of Profile Generation from Dialogues
https://github.com/ruiqixu37/BTTS_ECAI2023
공식 코드Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training
https://github.com/ruisun1/Mask-Predict-main
공식 코드An Error-Guided Correction Model for Chinese Spelling Error Correction
https://github.com/ruizheliUOA/TWR-VAE
공식 코드Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation
https://github.com/rungjoo/TransMC-data2text
공식 코드Transforming Multi-Conditioned Generation from Meaning Representation
https://github.com/ruqizhang/discrete-langevin
공식 코드https://github.com/russellliu0/rad
공식 코드https://github.com/russiannlp/rucola
공식 코드https://github.com/ryanzhumich/AESLC
공식 코드This Email Could Save Your Life: Introducing the Task of Email Subject Line Generation
https://github.com/rycolab/clusters-in-language-evaluation
공식 코드On the Usefulness of Embeddings, Clusters and Strings for Text Generator Evaluation
https://github.com/rycolab/sampling-adapters
공식 코드https://github.com/rycolab/uid-decoding
공식 코드https://github.com/ryuryukke/HowYouPromptMatters
공식 코드https://github.com/ryuryukke/OUTFOX
공식 코드https://github.com/rzhwang/infodiffusion
공식 코드InfoDiffusion: Information Entropy Aware Diffusion Process for Non-Autoregressive Text Generation
https://github.com/s-nlp/lewit-informal
공식 코드Don't lose the message while paraphrasing: A study on content preserving style transfer
https://github.com/s-sahoo/duo
공식 코드https://github.com/s2e-lab/llm-education-survey
공식 코드Large Language Models in Computer Science Education: A Systematic Literature Review
https://github.com/s6fikass/Chatbot_KVNN
공식 코드Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-Task Learning
https://github.com/safe-graph/graph-adversarial-learning-literature
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.