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/karins/CoherenceFramework
공식 코드https://github.com/karinseve/OTTers
공식 코드https://github.com/kasnerz/d2t_iterative_editing
공식 코드https://github.com/kasnerz/tabgenie
공식 코드https://github.com/kasnerz/zeroshot-d2t-pipeline
공식 코드https://github.com/katiefraser/pairs
공식 코드https://github.com/kaushal0494/ZmBART
공식 코드ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation
https://github.com/kaustpradalab/repeat-curse-llm
공식 코드Understanding the Repeat Curse in Large Language Models from a Feature Perspective
https://github.com/kayoyin/interpret-lm
공식 코드https://github.com/kedz/noiseylg
공식 코드https://github.com/kedz/styleeq
공식 코드Low-Level Linguistic Controls for Style Transfer and Content Preservation
https://github.com/keio-smilab22/relationalfuturecaptioningmodel
공식 코드Relational Future Captioning Model for Explaining Likely Collisions in Daily Tasks
https://github.com/kel-lu/scigen
공식 코드https://github.com/kepei1106/ARAML
공식 코드ARAML: A Stable Adversarial Training Framework for Text Generation
https://github.com/kepei1106/cbst
공식 코드Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation
https://github.com/kepei1106/decompeval
공식 코드DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering
https://github.com/kevinrojas1499/diffuse-everything
공식 코드Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
https://github.com/khuangaf/fakingfakenews
공식 코드Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation
https://github.com/kimho666/llm_hardware_survey
공식 코드Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
https://github.com/kingofspace0wzz/wae-rnf-lm
공식 코드Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling
https://github.com/kinit-sk/Crowd-vs-ChatGPT-Crowdsourcing-of-paraphrases-for-intent-classification
공식 코드https://github.com/kinit-sk/crowd-vs-gpt-intent-class
공식 코드https://github.com/kinit-sk/mAO
공식 코드Authorship Obfuscation in Multilingual Machine-Generated Text Detection
https://github.com/kiode/text_watermark_language_models
공식 코드https://github.com/kirubarajan/roft
공식 코드RoFT: A Tool for Evaluating Human Detection of Machine-Generated Text
https://github.com/kmc0207/Stableprompt
공식 코드StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models
https://github.com/knot-fit-but/oapapers
공식 코드https://github.com/knot-fit-but/oapapersviewer
공식 코드https://github.com/kohjingyu/fromage
공식 코드Grounding Language Models to Images for Multimodal Inputs and Outputs
https://github.com/kojima-takeshi188/lang_neuron
공식 코드https://github.com/komeijiforce/cotam
공식 코드Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation
https://github.com/kongds/mist
공식 코드https://github.com/koninik/diffusionpen
공식 코드DiffusionPen: Towards Controlling the Style of Handwritten Text Generation
https://github.com/koninik/wordstylist
공식 코드WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models
https://github.com/kotelnikov-ev/economic_argument_generation
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.