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/fuzihaofzh/distant_supervision_nlg
공식 코드Partially-Aligned Data-to-Text Generation with Distant Supervision
https://github.com/fuzihaofzh/repetition-problem-nlg
공식 코드A Theoretical Analysis of the Repetition Problem in Text Generation
https://github.com/fyyfu/headkv
공식 코드https://github.com/fyyfu/semantic-watermark
공식 코드https://github.com/gabeguo/any-order-speculative-decoding
공식 코드Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding
https://github.com/gabinsane/ald-vae
공식 코드Adaptive Compression of the Latent Space in Variational Autoencoders
https://github.com/gair-nlp/anole
공식 코드ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation
https://github.com/gair-nlp/mops
공식 코드MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation
https://github.com/galirage/gpr-bench
공식 코드https://github.com/geek-ai/Texygen
공식 코드https://github.com/georgedrayson/model_collapse
공식 코드Machine-generated text detection prevents language model collapse
https://github.com/georgevern/lmcor
공식 코드Small Language Models Improve Giants by Rewriting Their Outputs
https://github.com/geri-emp/CAB
공식 코드CAB: Empathetic Dialogue Generation with Cognition, Affection and Behavior
https://github.com/geshang777/pix2cap
공식 코드Pix2Cap-COCO: Advancing Visual Comprehension via Pixel-Level Captioning
https://github.com/ghazi-f/qkvae
공식 코드https://github.com/ghosthamlet/persona
공식 코드Improvement of a dedicated model for open domain persona-aware dialogue generation
https://github.com/ghrua/ngramres
공식 코드$N$-gram Is Back: Residual Learning of Neural Text Generation with $n$-gram Language Model
https://github.com/gicheonkang/gst-visdial
공식 코드The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training
https://github.com/gingasan/lemon
공식 코드Rethinking Masked Language Modeling for Chinese Spelling Correction
https://github.com/giobin/applied_intelligence_sparsity
공식 코드Regularization-based Pruning of Irrelevant Weights in Deep Neural Architectures
https://github.com/githubhyz/DischargeMe_BioNLP2024
공식 코드https://github.com/gkuwanto/ezswitch
공식 코드https://github.com/gmago-leway/fewshotgec
공식 코드Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction
https://github.com/gmftbygmftby/copyisallyouneed
공식 코드https://github.com/gmftbygmftby/momentumdecoding
공식 코드Momentum Decoding: Open-ended Text Generation As Graph Exploration
https://github.com/gmum/plugen
공식 코드PluGeN: Multi-Label Conditional Generation From Pre-Trained Models
https://github.com/godfire66666/llm_rec_explanation
공식 코드Unlocking the Potential of Large Language Models for Explainable Recommendations
https://github.com/google-deepmind/dramatron
공식 코드https://github.com/google-research-datasets/KELM-corpus
공식 코드Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training
https://github.com/google-research-datasets/NewsQuizQA
공식 코드https://github.com/google-research-datasets/ToTTo
공식 코드https://github.com/google-research-datasets/aquamuse
공식 코드AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization
https://github.com/google-research-datasets/clse
공식 코드https://github.com/google-research-datasets/quotesum
공식 코드https://github.com/google-research-datasets/xsum_hallucination_annotations
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.