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/opennlplab/favdbench
공식 코드https://github.com/openvinotoolkit/openvino_notebooks
공식 코드Leveraging Speculative Sampling and KV-Cache Optimizations Together for Generative AI using OpenVINO
https://github.com/openvlg/della
공식 코드https://github.com/oriern/SPARK
공식 코드https://github.com/oriern/SuperPAL
공식 코드Summary-Source Proposition-level Alignment: Task, Datasets and Supervised Baseline
https://github.com/oriern/clusterprop
공식 코드Proposition-Level Clustering for Multi-Document Summarization
https://github.com/oriern/procluster
공식 코드Proposition-Level Clustering for Multi-Document Summarization
https://github.com/oswald1997/glimmer
공식 코드GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization
https://github.com/oswaldoludwig/Adversarial-Learning-for-Generative-Conversational-Agents
공식 코드End-to-end Adversarial Learning for Generative Conversational Agents
https://github.com/oswaldoludwig/Seq2seq-Chatbot-for-Keras
공식 코드End-to-end Adversarial Learning for Generative Conversational Agents
https://github.com/oxai/intersectional_gpt2
공식 코드https://github.com/pablomessina/cxr-fact-encoder
공식 코드https://github.com/palchenli/TVD
공식 코드PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas
https://github.com/panlingua/multilingual-tst-datasets
공식 코드Multilingual Text Style Transfer: Datasets & Models for Indian Languages
https://github.com/parameterlab/apricot
공식 코드Calibrating Large Language Models Using Their Generations Only
https://github.com/pascalson/causaldialogue
공식 코드CausalDialogue: Modeling Utterance-level Causality in Conversations
https://github.com/passerby233/VSCMR-Visual-Storytelling-with-Corss-Modal-Rules
공식 코드https://github.com/patrick-tssn/VSTAR
공식 코드https://github.com/patrickamadeus/vqa-nle-llava
공식 코드Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models
https://github.com/patuchen/nlg_metric_usage
공식 코드Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices
https://github.com/paulkmandal/fnet_news_headlines
공식 코드An FNet based Auto Encoder for Long Sequence News Story Generation
https://github.com/pavanbaswani/fincausal_sharedtask-2023
공식 코드https://github.com/pclucas14/GansFallingShort
공식 코드https://github.com/pedramsalimi/nlgxai
공식 코드Towards Feasible Counterfactual Explanations: A Taxonomy Guided Template-based NLG Method
https://github.com/pengbaolin/SC-GPT
공식 코드Few-shot Natural Language Generation for Task-Oriented Dialog
https://github.com/persist-lab/syntheticportalgen
공식 코드https://github.com/persona-bench/persona
공식 코드A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations
https://github.com/peterbhase/poetry-generation
공식 코드Shall I Compare Thee to a Machine-Written Sonnet? An Approach to Algorithmic Sonnet Generation
https://github.com/peterfengyx/dunst
공식 코드DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation
https://github.com/peterfengyx/kest
공식 코드KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation
https://github.com/petergriffinjin/search-r1
공식 코드Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
https://github.com/peterliwenhao/care
공식 코드https://github.com/pfnet-research/pfgen-bench
공식 코드A Judge-free LLM Open-ended Generation Benchmark Based on the Distributional Hypothesis
https://github.com/pgraphrag-benchmark/pgr-llm
공식 코드Personalized Graph-Based Retrieval for Large Language Models
https://github.com/phvv-me/frame-representation-hypothesis
공식 코드Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.