https://github.com/launchnlp/bolt
공식 코드BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases
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/launchnlp/litcab
공식 코드LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses
https://github.com/lblaoke/CARDS
공식 코드Cascade Reward Sampling for Efficient Decoding-Time Alignment
https://github.com/lddsdu/VRBot
공식 코드Semi-Supervised Variational Reasoning for Medical Dialogue Generation
https://github.com/leehaoyuan/coverage_fairness
공식 코드https://github.com/lemmonation/abnet
공식 코드Incorporating BERT into Parallel Sequence Decoding with Adapters
https://github.com/lemon234071/AdaLabel
공식 코드https://github.com/lemonqc/kg2text
공식 코드Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency
https://github.com/lemonsis/ctrlstruct
공식 코드CTRLStruct: Dialogue Structure Learning for Open-Domain Response Generation
https://github.com/lemonsis/mdd-5k
공식 코드https://github.com/lemuria-wchen/dxformer
공식 코드https://github.com/lennart-finke/simple_stories_generate
공식 코드https://github.com/leo-yangli/vb-lora
공식 코드VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
https://github.com/leondz/lm_risk_cards
공식 코드https://github.com/leshanbog/PreSumm
공식 코드Advances of Transformer-Based Models for News Headline Generation
https://github.com/lezhang7/retrieval_mugi
공식 코드Exploring the Best Practices of Query Expansion with Large Language Models
https://github.com/lflage/openfactscore
공식 코드OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation
https://github.com/lgw863/acsa-generation
공식 코드Solving Aspect Category Sentiment Analysis as a Text Generation Task
https://github.com/lhryang/crl_egpg
공식 코드Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation
https://github.com/lhryang/fsd
공식 코드A Frustratingly Simple Decoding Method for Neural Text Generation
https://github.com/liang-star177/kig
공식 코드Enhancing Court View Generation with Knowledge Injection and Guidance
https://github.com/liang8qi/plan-then-seam
공식 코드https://github.com/liangzh63/dorm-csc
공식 코드Disentangled Phonetic Representation for Chinese Spelling Correction
https://github.com/liangzid/MERGE
공식 코드https://github.com/liatschiff/openasp
공식 코드OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarization
https://github.com/lichengunc/refer
공식 코드https://github.com/lifebench/lifebench
공식 코드LIFEBench: Evaluating Length Instruction Following in Large Language Models
https://github.com/lifestrugglee/privacy-synthetic-generation
공식 코드https://github.com/lijm48/imccd
공식 코드https://github.com/lijuncen/Sentiment-and-Style-Transfer
공식 코드Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
https://github.com/lileipisces/PETER
공식 코드https://github.com/lileipisces/pepler
공식 코드https://github.com/linear95/rlm
공식 코드https://github.com/lingo-iitgn/Bollyrics
공식 코드https://github.com/linguisticanomalies/appls
공식 코드APPLS: Evaluating Evaluation Metrics for Plain Language Summarization
https://github.com/linguisticanomalies/pls_retrieval
공식 코드Retrieval augmentation of large language models for lay language generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.