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/microsoft/plog
공식 코드PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation
https://github.com/microsoft/scglab
공식 코드https://github.com/microsoft/semantic_parsing_with_constrained_lm
공식 코드BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing
https://github.com/microsoft/unilm
공식 코드Unified Language Model Pre-training for Natural Language Understanding and Generation
https://github.com/microsoft/unilm/tree/master/deltalm
공식 코드https://github.com/microsoft/unilm/tree/master/trocr
공식 코드TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
https://github.com/microsofttranslator/ntrex
공식 코드A Benchmark for Evaluating Machine Translation Metrics on Dialects Without Standard Orthography
https://github.com/milanlproc/language-invariant-properties
공식 코드Language Invariant Properties in Natural Language Processing
https://github.com/milteam/MedSyn
공식 코드MedSyn: LLM-based Synthetic Medical Text Generation Framework
https://github.com/mimify/ss-gen
공식 코드SS-GEN: A Social Story Generation Framework with Large Language Models
https://github.com/minamar/rebl-pepper-data
공식 코드Data-driven emotional body language generation for social robotics
https://github.com/mingdachen/WikiTableT
공식 코드WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections
https://github.com/mingdachen/mVGVAE
공식 코드Exemplar-Controllable Paraphrasing and Translation using Bitext
https://github.com/mingdachen/syntactic-template-generation
공식 코드Leveraging Natural Supervision for Language Representation Learning and Generation
https://github.com/mingdachen/tvrecap
공식 코드TVStoryGen: A Dataset for Generating Stories with Character Descriptions
https://github.com/mingjianjiang-1/graph-based-uncertainty
공식 코드Graph-based Uncertainty Metrics for Long-form Language Model Outputs
https://github.com/mingkaid/rl-prompt
공식 코드RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
https://github.com/mingxiao-li/asymmetry-zigzag-storydiffusion
공식 코드https://github.com/mingzi151/SummPip
공식 코드SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression
https://github.com/minjiyoon/mmgl
공식 코드https://github.com/minnesotanlp/co-taxonomy
공식 코드Human-AI Collaborative Taxonomy Construction: A Case Study in Profession-Specific Writing Assistants
https://github.com/minnesotanlp/reward-system
공식 코드Decoding the End-to-end Writing Trajectory in Scholarly Manuscripts
https://github.com/mintelligence-group/cmfeed
공식 코드Synthesizing Sentiment-Controlled Feedback For Multimodal Text and Image Data
https://github.com/mio-team/mio
공식 코드https://github.com/mir-mu/softalign_objectives
공식 코드Soft Alignment Objectives for Robust Adaptation of Language Generation
https://github.com/mirah-official/empathetic-chatbot-asem
공식 코드ASEM: Enhancing Empathy in Chatbot through Attention-based Sentiment and Emotion Modeling
https://github.com/mireshghallah/mixmatch
공식 코드Mix and Match: Learning-free Controllable Text Generation using Energy Language Models
https://github.com/mismayil/creative-story-gen
공식 코드Evaluating Creative Short Story Generation in Humans and Large Language Models
https://github.com/misonsky/Amdg
공식 코드A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation
https://github.com/mitvis/vistext
공식 코드https://github.com/miulab/salesbot
공식 코드SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues
https://github.com/mk-runner/FSE
공식 코드Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation
https://github.com/mk-runner/sei
공식 코드https://github.com/mk322/ever_hallu
공식 코드https://github.com/mkremins/spleenwort
공식 코드Guiding and Diversifying LLM-Based Story Generation via Answer Set Programming
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.