https://github.com/uh-serg/ci-memorization
공식 코드Memorization and Generalization in Neural Code Intelligence Models
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/uhh-lt/par4Acad
공식 코드https://github.com/uic-nlp-lab/virtualcoachdata
공식 코드https://github.com/uiucnlp/mumuqa
공식 코드https://github.com/ujjwalaananth/edm3_eventdetection
공식 코드https://github.com/ukplab/citebench
공식 코드CiteBench: A benchmark for Scientific Citation Text Generation
https://github.com/ukplab/emnlp2022-reasoning-aware-pretraining
공식 코드Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models
https://github.com/ukplab/emnlp2023-learning-from-free-text-human-feedback
공식 코드Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?
https://github.com/ukplab/iclr2025-psa
공식 코드Differentially Private Steering for Large Language Model Alignment
https://github.com/ukplab/m-amr2text
공식 코드Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation
https://github.com/ukplab/starsem2023-arithmetic-based-pretraining
공식 코드Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models
https://github.com/ukplab/structadapt
공식 코드Structural Adapters in Pretrained Language Models for AMR-to-text Generation
https://github.com/umass-ml4ed/divert
공식 코드https://github.com/umass-ml4ed/prompt_distractor_generation_naacl
공식 코드https://github.com/umd-huang-lab/vlm-poisoning
공식 코드Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
https://github.com/uridr/gtwiki
공식 코드A multi-task semi-supervised framework for Text2Graph & Graph2Text
https://github.com/usc-fortis/ad-llm
공식 코드AD-LLM: Benchmarking Large Language Models for Anomaly Detection
https://github.com/user683/hnlmrec
공식 코드Can LLM-Driven Hard Negative Sampling Empower Collaborative Filtering? Findings and Potentials
https://github.com/usydnlp/rovist
공식 코드https://github.com/uzh-dqbm-cmi/argon
공식 코드Progressive Transformer-Based Generation of Radiology Reports
https://github.com/vaderasu/geoexplainer
공식 코드https://github.com/valdersoul/bn-vae
공식 코드A Batch Normalized Inference Network Keeps the KL Vanishing Away
https://github.com/vectorspacelab/omnigen
공식 코드https://github.com/vectorspacelab/omnigen2
공식 코드https://github.com/vedantpalit/towards-vision-language-mechanistic-interpretability
공식 코드Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP
https://github.com/vegb/inlg
공식 코드Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
https://github.com/vejvarm/aspiro
공식 코드ASPIRO: Any-shot Structured Parsing-error-Induced ReprOmpting for Consistent Data-to-Text Generation
https://github.com/venkatasg/Advice-EMNLP2020
공식 코드https://github.com/veranep/crosslingualdetoxdebias
공식 코드https://github.com/veronicium/doclens
공식 코드DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation
https://github.com/vicgalle/zero-shot-reward-models
공식 코드ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF
https://github.com/victorup/SoCP
공식 코드Controllable Multi-Character Psychology-Oriented Story Generation
https://github.com/victorup/ToViLaG
공식 코드ToViLaG: Your Visual-Language Generative Model is Also An Evildoer
https://github.com/victorup/chae
공식 코드CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions
https://github.com/victorwz/tod_as_nlg
공식 코드Task-Oriented Dialogue System as Natural Language Generation
https://github.com/videocrafter/animate-a-story
공식 코드Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.