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/acolas1/EventNarrative
공식 코드EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text Generation
https://github.com/acolas1/GAP_COLING2022
공식 코드GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation
https://github.com/acolas1/kgsimple
공식 코드https://github.com/ad-freiburg/tokenization-repair
공식 코드https://github.com/adauchendu/topformer
공식 코드TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles
https://github.com/adbrei/renargen
공식 코드Returning to the Start: Generating Narratives with Related Endpoints
https://github.com/adelaidehsu/rec
공식 코드https://github.com/adiallo07/pizzacommonsense
공식 코드https://github.com/adianliusie/comparative-assessment
공식 코드https://github.com/adithya7/hybrid-rag
공식 코드Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization
https://github.com/adithya7/lambre
공식 코드Evaluating the Morphosyntactic Well-formedness of Generated Texts
https://github.com/adithya7/scaling-mds
공식 코드Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches
https://github.com/aditya12agd5/convcap
공식 코드https://github.com/adlnlp/MultimodalLLM
공식 코드Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and Beyond
https://github.com/ads-ai/paraqd
공식 코드https://github.com/aehrc/cvt2distilgpt2
공식 코드Improving Chest X-Ray Report Generation by Leveraging Warm Starting
https://github.com/aeshapar/gender-seniority-compound-bias-dataset
공식 코드Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation
https://github.com/afraamini/svs
공식 코드https://github.com/afrozas/skip-thought-gan
공식 코드Generating Text through Adversarial Training using Skip-Thought Vectors
https://github.com/agemagician/CodeTrans
공식 코드https://github.com/agiresearch/idgenrec
공식 코드https://github.com/agnesion/zero-shot-nlg-from-kgs-data
공식 코드Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs
https://github.com/ago109/piecewise-nvdm-emnlp-2017
공식 코드Piecewise Latent Variables for Neural Variational Text Processing
https://github.com/ahclab/reflection
공식 코드https://github.com/ahtsham58/crb-crs
공식 코드https://github.com/ahwang16/grounded-intuition-gpt-vision
공식 코드Grounded Intuition of GPT-Vision's Abilities with Scientific Images
https://github.com/ahwang16/mturk-templates
공식 코드Large Language Models as Sous Chefs: Revising Recipes with GPT-3
https://github.com/ai-forever/sage
공식 코드https://github.com/ai-in-health/clinicbench
공식 코드Large Language Models in the Clinic: A Comprehensive Benchmark
https://github.com/ai-vtrc/exclaim
공식 코드ExClaim: Explainable Neural Claim Verification Using Rationalization
https://github.com/ai21labs/in-context-ralm
공식 코드https://github.com/ai4bharat/fbi
공식 코드Finding Blind Spots in Evaluator LLMs with Interpretable Checklists
https://github.com/aigents/aigents-java-nlp
공식 코드Natural Language Generation Using Link Grammar for General Conversational Intelligence
https://github.com/aigtext/glyphcontrol-release
공식 코드GlyphControl: Glyph Conditional Control for Visual Text Generation
https://github.com/aiha-lab/tsld
공식 코드Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.