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/neulab/compare-mt
공식 코드compare-mt: A Tool for Holistic Comparison of Language Generation Systems
https://github.com/neuralchecker/analyzing_constrained_llm_through_pdfa_learning
공식 코드https://github.com/neuspeech/mad-meg2text
공식 코드https://github.com/neuspeech/neugpt
공식 코드https://github.com/neuspell/neuspell
공식 코드https://github.com/nghuyong/cscd-ime
공식 코드CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers
https://github.com/nguyenvo09/LearningFromFactCheckers
공식 코드Learning from Fact-checkers: Analysis and Generation of Fact-checking Language
https://github.com/ngwgsang/visp
공식 코드https://github.com/nhathoang2002/toxcl
공식 코드ToXCL: A Unified Framework for Toxic Speech Detection and Explanation
https://github.com/nianlonggu/lmcitegen
공식 코드Controllable Citation Sentence Generation with Language Models
https://github.com/nickdeas/masive
공식 코드MASIVE: Open-Ended Affective State Identification in English and Spanish
https://github.com/nicofirst1/speaker-adaptation
공식 코드Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind
https://github.com/nicolaffETHZ/Brain2Word_paper
공식 코드https://github.com/nicpopovic/ember
공식 코드https://github.com/nicpopovic/stoke
공식 코드https://github.com/niejiahao1998/mmrel
공식 코드https://github.com/nighood/SynAlign
공식 코드https://github.com/nika2312/qa_explaination
공식 코드Explaining Question Answering Models through Text Generation
https://github.com/nikhilbyte/hinglish-qeval
공식 코드https://github.com/nil-zhuang/ld4pg
공식 코드Improved Paraphrase Generation via Controllable Latent Diffusion
https://github.com/ninarehm/robust-agents
공식 코드Robust Conversational Agents against Imperceptible Toxicity Triggers
https://github.com/nish-19/persona-story-gen
공식 코드Whose story is it? Personalizing story generation by inferring author styles
https://github.com/nishantsubramani/steering_vectors
공식 코드Extracting Latent Steering Vectors from Pretrained Language Models
https://github.com/nitaytech/kd4gen
공식 코드https://github.com/niveck/LLMafia
공식 코드Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games
https://github.com/nju-pcalab/textcrafter
공식 코드TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes
https://github.com/nju-websoft/dift
공식 코드https://github.com/nju-websoft/magic
공식 코드Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation
https://github.com/njunlp/knn-box
공식 코드kNN-BOX: A Unified Framework for Nearest Neighbor Generation
https://github.com/nkluge-correa/teenytinyllama
공식 코드TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese
https://github.com/nkluge-correa/tucano
공식 코드https://github.com/nl2g/effeval
공식 코드EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics
https://github.com/nlgcat/evaluating_accuracy
공식 코드A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems
https://github.com/nlp-rl/semtextuallogue-loss
공식 코드https://github.com/nlp-titech/headline-entailment
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.