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/piquil/rydberggpt
https://github.com/pko89403/llm-for-recsys-shadow/tree/main/E4SRec
https://github.com/plkmo/Transformer-Eng2French
https://github.com/pluslabnlp/aesop
https://github.com/pnshiralkar/text-to-handwriting
https://github.com/poethan/cushLEPOR
Translation Quality Assessment: A Brief Survey on Manual and Automatic Methods
https://github.com/pomonam/AttentionCluster
https://github.com/ppchavan/chitchatbot1
Personalizing Dialogue Agents: I have a dog, do you have pets too?
https://github.com/prabhupad26/100daysofML
https://github.com/prachetaphadnis/NMT_Seq2Seq_LexicalModel
Effective Approaches to Attention-based Neural Machine Translation
https://github.com/prakhargurawa/Neural-Machine-Translation-Keras-Attention
Neural Machine Translation by Jointly Learning to Align and Translate
https://github.com/prakhargurawa/Neural-Machine-Translation-Keras-German-English
Neural Machine Translation by Jointly Learning to Align and Translate
https://github.com/pranavgollamudi/Chatbot
TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
https://github.com/prapti19/prompt_autohint
AutoHint: Automatic Prompt Optimization with Hint Generation
https://github.com/prashanth41/text-summarization
https://github.com/prathameshza/TrOCR_FineTuning
TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
https://github.com/praveenjune17/BERT_text_summarisation
Pretraining-Based Natural Language Generation for Text Summarization
https://github.com/previtus/fake_news_generation_mark_I
https://github.com/primeqa/primeqa
https://github.com/princeton-nlp/mabel
HuggingFace's Transformers: State-of-the-art Natural Language Processing
https://github.com/pritam1322/Machine-Translation-with-Transformer
https://github.com/prithivirajdamodaran/styleformer
Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
https://github.com/prithvi2226/Bilingual-Sentiment-Analysis
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations
https://github.com/priyamtejaswin/multistep-retrieve-summarize
https://github.com/project-basileus/multitype-sequence-generation-by-tlstm-gan
SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
https://github.com/pseulki/rococo
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/pskrunner14/descriptor
https://github.com/pumpkinman008/StoryGeneration
https://github.com/pushpendughosh/Stock-market-forecasting
Neural Paraphrase Generation with Stacked Residual LSTM Networks
https://github.com/pwc-1/Paper-10/tree/main/trocr
TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
https://github.com/pwc-1/Paper-5/tree/main/mbart50
IndicBART: A Pre-trained Model for Indic Natural Language Generation
https://github.com/pwc-1/Paper-5/tree/main/moss
MOSS: End-to-End Dialog System Framework with Modular Supervision
https://github.com/pwc-1/Paper-5/tree/main/mvp
MVP: Multi-task Supervised Pre-training for Natural Language Generation
https://github.com/pwc-1/Paper-8/tree/main/clip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/pwc-1/Paper-9/tree/main/1/trocr
TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.