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/msakarvadia/attentionlens
공식 코드Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning
https://github.com/msalhab96/AraSpell
공식 코드AraSpell: A Deep Learning Approach for Arabic Spelling Correction
https://github.com/mt-upc/logit-explanations
공식 코드Explaining How Transformers Use Context to Build Predictions
https://github.com/mtsomethree/constrdecoding
공식 코드Controllable Text Generation with Neurally-Decomposed Oracle
https://github.com/mttn2023/mttn
공식 코드MTTN: Multi-Pair Text to Text Narratives for Prompt Generation
https://github.com/mu-cai/TemporalBench
공식 코드TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
https://github.com/mudabek/encoding-cxr-report-gen
공식 코드On the Importance of Image Encoding in Automated Chest X-Ray Report Generation
https://github.com/multilexsum/dataset
공식 코드Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities
https://github.com/mutonix/refgpt
공식 코드https://github.com/muyeby/AMR-Backparsing
공식 코드https://github.com/muyeby/amrbart
공식 코드https://github.com/mxschmdt/mrqa-gen-al
공식 코드Combining Data Generation and Active Learning for Low-Resource Question Answering
https://github.com/my625/cot-mcqgen
공식 코드A Novel Multi-Stage Prompting Approach for Language Agnostic MCQ Generation using GPT
https://github.com/mya-mya/cbf-llm
공식 코드https://github.com/myazann/ap-bots
공식 코드Improving RAG for Personalization with Author Features and Contrastive Examples
https://github.com/myracheng/markedpersonas
공식 코드Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models
https://github.com/naist-nlp/mbrs
공식 코드https://github.com/namco0816/proxyqa
공식 코드https://github.com/nathangodey/qfilters
공식 코드Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
https://github.com/naver-ai/korean-safety-benchmarks
공식 코드KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application
https://github.com/naver/gdc
공식 코드https://github.com/nayeon7lee/factualityprompt
공식 코드Factuality Enhanced Language Models for Open-Ended Text Generation
https://github.com/naylenv/uf-fgtg
공식 코드A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis
https://github.com/naymyatmin/crow
공식 코드CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
https://github.com/nazmul-karim170/FIP-Fisher-Backdoor-Removal
공식 코드Fisher Information guided Purification against Backdoor Attacks
https://github.com/nbalepur/expository-text-generation
공식 코드https://github.com/nbalepur/text-fact-transfer
공식 코드https://github.com/ncsoft/cap2qa
공식 코드https://github.com/ndaheim/faithful-dialogue
공식 코드Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
https://github.com/nealcly/ke-blender
공식 코드Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation
https://github.com/neato47/neural-numeric-to-text-generation
공식 코드Towards Neural Numeric-To-Text Generation From Temporal Personal Health Data
https://github.com/neelabhsinha/qa-prompting
공식 코드QA-prompting: Improving Summarization with Large Language Models using Question-Answering
https://github.com/networkslab/enlsp_neurips24
공식 코드https://github.com/neukg/kat-tslf
공식 코드A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
https://github.com/neulab/BARTScore
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.