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/amazon-science/wqa-controlled-text-generation
공식 코드Controlled Text Generation with Hidden Representation Transformations
https://github.com/aminbigdeli/empra
공식 코드EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models
https://github.com/aminkaramlou/qnlg
공식 코드https://github.com/amirbar/rnn.wgan
공식 코드Language Generation with Recurrent Generative Adversarial Networks without Pre-training
https://github.com/andreamad8/ToDCL
공식 코드https://github.com/andy194673/Joint-NLU-NLG
공식 코드A Generative Model for Joint Natural Language Understanding and Generation
https://github.com/andychiangsh/cdgp
공식 코드CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model
https://github.com/andyjliu/persona-steered-generation-bias
공식 코드Evaluating Large Language Model Biases in Persona-Steered Generation
https://github.com/anindyasdas/selfsupervisedimagetext
공식 코드https://github.com/ankanbhunia/Handwriting-Transformers
공식 코드https://github.com/anon23423589675234/zero-shot-reward-models
공식 코드ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF
https://github.com/anonno2/crosstalk-generation
공식 코드Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk
https://github.com/anonymous-1759/eqhard-em
공식 코드An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation
https://github.com/anonymous1100/D_Improves_G_without_Updating_G
공식 코드Adding A Filter Based on The Discriminator to Improve Unconditional Text Generation
https://github.com/anonymous1100/Distributional-Discrepancy
공식 코드Distributional Discrepancy: A Metric for Unconditional Text Generation
https://github.com/anonymousakes/differentially-private-fine-tuning-of-language-models
공식 코드https://github.com/anonymousanoy/fohe
공식 코드https://github.com/anoopkdcs/affective_bias_in_plm
공식 코드https://github.com/anpoc/language-models-in-medicine
공식 코드Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings
https://github.com/anranwu-richpo/dcqa
공식 코드https://github.com/ant-research/structuredlm_rtdt
공식 코드Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale
https://github.com/anthonysicilia/equitable-dialogue-acl2023
공식 코드Learning to Generate Equitable Text in Dialogue from Biased Training Data
https://github.com/anthonysicilia/leather-aacl2022
공식 코드LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue
https://github.com/anthonywchen/rarr
공식 코드RARR: Researching and Revising What Language Models Say, Using Language Models
https://github.com/aolius/semi-fst
공식 코드Semi-Supervised Formality Style Transfer with Consistency Training
https://github.com/aoshuang92/css_uq_llms
공식 코드CSS: Contrastive Semantic Similarity for Uncertainty Quantification of LLMs
https://github.com/aplesner/flip-reasoning-challenge
공식 코드https://github.com/apple/ml-sage-dialog-gen
공식 코드SAGE: Steering and Refining Dialog Generation with State-Action Augmentation
https://github.com/apple/ml-selfcond
공식 코드https://github.com/apple/ml-tweak
공식 코드Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation
https://github.com/appleternity/story-plot-generation
공식 코드Conveying the Predicted Future to Users: A Case Study of Story Plot Prediction
https://github.com/arenaa/accelerated-generation-techniques
공식 코드A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models
https://github.com/argonne-lcf/llm-inference-bench
공식 코드LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators
https://github.com/ariecattan/multi_mds
공식 코드https://github.com/ariecattan/qasem_consistency
공식 코드Localizing Factual Inconsistencies in Attributable Text Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.