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/haiyangzheng/textgcd
공식 코드Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery
https://github.com/halfrot/ALaRM
공식 코드ALaRM: Align Language Models via Hierarchical Rewards Modeling
https://github.com/hallerpatrick/pecc
공식 코드https://github.com/hanane-djeddal/complex-answer-generation
공식 코드Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs
https://github.com/hanjiale/genpt
공식 코드https://github.com/hannibal046/selfmemory
공식 코드Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory
https://github.com/hanqi-qi/matte
공식 코드https://github.com/hanscal/dcks
공식 코드Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge
https://github.com/hansolo9682/countercurate
공식 코드https://github.com/hanxuhu/controllt2trobust
공식 코드Improving User Controlled Table-To-Text Generation Robustness
https://github.com/haoningwu3639/StoryGen
공식 코드Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models
https://github.com/haounsw/pisa
공식 코드PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting
https://github.com/happen2me/cross-gnn
공식 코드GraphextQA: A Benchmark for Evaluating Graph-Enhanced Large Language Models
https://github.com/happygu0524/multicontrol
공식 코드A Distributional Lens for Multi-Aspect Controllable Text Generation
https://github.com/harsh19/Latent-Anchor-Plan
공식 코드https://github.com/harshraj172/measuring-reliability-of-llms
공식 코드Measuring Reliability of Large Language Models through Semantic Consistency
https://github.com/harvardnlp/BSO
공식 코드https://github.com/harvardnlp/boxscore-data
공식 코드https://github.com/harvardnlp/cascaded-generation
공식 코드https://github.com/harvardnlp/data2text
공식 코드https://github.com/harvardnlp/encoder-agnostic-adaptation
공식 코드Encoder-Agnostic Adaptation for Conditional Language Generation
https://github.com/harvardnlp/neural-template-gen
공식 코드https://github.com/harvardnlp/sa-vae
공식 코드https://github.com/hasiburshanto/bangla-spell-checker
공식 코드https://github.com/hazyresearch/based
공식 코드Simple linear attention language models balance the recall-throughput tradeoff
https://github.com/hazyresearch/zoology
공식 코드Simple linear attention language models balance the recall-throughput tradeoff
https://github.com/hcplab-sysu/personsearch-ctlg
공식 코드Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search
https://github.com/he159ok/benchmark-of-uncertainty-estimation-methods-in-text-summarization
공식 코드Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?
https://github.com/healthylaife/ConTextual
공식 코드https://github.com/heegyukim/gta
공식 코드GTA: Gated Toxicity Avoidance for LM Performance Preservation
https://github.com/hehedaozuiteng/chinese-story-generation
공식 코드Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics
https://github.com/hellisotherpeople/constrained-text-generation-studio
공식 코드https://github.com/hendrycks/math
공식 코드Measuring Mathematical Problem Solving With the MATH Dataset
https://github.com/hengyicai/AdaND
공식 코드https://github.com/hengyicai/Adaptive_Multi-curricula_Learning_for_Dialog
공식 코드Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.