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/thefonseca/factorsum
https://github.com/thinkwee/DPP_CNN_Summarization
https://github.com/thomashuang2017/simpson-dialogue-gan-master
https://github.com/thomlake/pytorch-attention
Neural Machine Translation by Jointly Learning to Align and Translate
https://github.com/thorMax/AIPaperWriter
PaperRobot: Incremental Draft Generation of Scientific Ideas
https://github.com/thu-esis/jiuzhou
TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks
https://github.com/thu-keg/korc
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
https://github.com/thudm/longwriter
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
https://github.com/thudm/swissarmytransformer
https://github.com/thudm/visualglm-6b
https://github.com/thumt/THUMT
Neural Machine Translation by Jointly Learning to Align and Translate
https://github.com/thunlp-mt/ckd
Neural Machine Translation by Jointly Learning to Align and Translate
https://github.com/thunlp/TensorFlow-Summarization
Neural Machine Translation by Jointly Learning to Align and Translate
https://github.com/thunlp/chateval
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
https://github.com/timbmg/DIAL-LV
https://github.com/timrozday/spl-indications-bart
https://github.com/tjrwlgns1198/ChatBot
https://github.com/tomdyer10/fake_news
https://github.com/tomekkorbak/pretraining-with-human-feedback
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
https://github.com/toneli/rt-retrieving-and-thinking
https://github.com/tongbao96/code-for-sfr-as
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
https://github.com/towhee-io/towhee
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/trailofbits/privacyraven
https://github.com/tree-park/kor-to-eng-translation
Neural Machine Translation by Jointly Learning to Align and Translate
https://github.com/tree-park/transformer_lm
https://github.com/triton-inference-server/fastertransformer_backend
Factuality Enhanced Language Models for Open-Ended Text Generation
https://github.com/truclycs/ocr_seq2seq
https://github.com/tshu-w/dbcopilot
https://github.com/tshu-w/llm4em
https://github.com/turbo-llm/turbo-alignment
ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood
https://github.com/tuvuumass/SCoPE
A Hierarchical Neural Autoencoder for Paragraphs and Documents
https://github.com/tvinith/bert
https://github.com/tyliupku/HaDeS
A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation
https://github.com/tyxr/bert
https://github.com/u7javed/Transformer-Multi-Language-Translator
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.