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/believewhat/dr.noteaid
공식 코드NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes
https://github.com/belindal/state-probes
공식 코드Implicit Representations of Meaning in Neural Language Models
https://github.com/berlino/grammar-prompting
공식 코드Grammar Prompting for Domain-Specific Language Generation with Large Language Models
https://github.com/bernard-yang/distilltablecot
공식 코드Effective Distillation of Table-based Reasoning Ability from LLMs
https://github.com/bernard-yang/meddiaamr
공식 코드Improving Medical Dialogue Generation with Abstract Meaning Representations
https://github.com/bernardoleite/few-shot-prompting-qg-control
공식 코드On Few-Shot Prompting for Controllable Question-Answer Generation in Narrative Comprehension
https://github.com/beyondguo/genius
공식 코드https://github.com/bfshi/toast
공식 코드https://github.com/bigai-ai/ICE
공식 코드In-Context Editing: Learning Knowledge from Self-Induced Distributions
https://github.com/bigheiniu/FactGen
공식 코드https://github.com/billchan226/halc
공식 코드HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
https://github.com/bkane2/habitual-response-generation
공식 코드We are what we repeatedly do: Inducing and deploying habitual schemas in persona-based responses
https://github.com/blbadger/maskedmixers
공식 코드https://github.com/blitzprecision/ficle
공식 코드Neural models for Factual Inconsistency Classification with Explanations
https://github.com/blmoistawinde/dasc
공식 코드Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation
https://github.com/bnewm0609/comm-eval
공식 코드Communication-based Evaluation for Natural Language Generation
https://github.com/bohanhou14/semstamp
공식 코드SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
https://github.com/borgr/IBGEC
공식 코드https://github.com/borgr/nematus
공식 코드Enhancing the Transformer Decoder with Transition-based Syntax
https://github.com/botong516/conformal_structured_prediction
공식 코드https://github.com/bpucla/ibebm
공식 코드Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification
https://github.com/bradyfu/awesome-multimodal-large-language-models
공식 코드HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
https://github.com/brit7777/lm-plagiarism
공식 코드https://github.com/bscho333/ReVisiT
공식 코드https://github.com/budzianowski/multiwoz
공식 코드Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
https://github.com/bui1dmysea/memlong
공식 코드https://github.com/butterfliesss/EmpRL
공식 코드Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation
https://github.com/byliutao/1prompt1story
공식 코드One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
https://github.com/bytedance/1d-tokenizer
공식 코드https://github.com/bytedance/textharmony
공식 코드https://github.com/c-juhwan/multi_news_plus
공식 코드Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation
https://github.com/c-rajan/Multi-source-NewsSummarization
공식 코드Shaping Political Discourse using multi-source News Summarization
https://github.com/c4ai/blab-reporter
공식 코드BLAB Reporter: Automated journalism covering the Blue Amazon
https://github.com/caiqizh/LUQ
공식 코드https://github.com/caiyuhu/MCiteBench
공식 코드MCiteBench: A Multimodal Benchmark for Generating Text with Citations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.