https://github.com/xxbidiao/plug-and-blend
공식 코드Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes
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/xydaytoy/eva
공식 코드Bridging the Gap between Different Vocabularies for LLM Ensemble
https://github.com/xz-liu/shield
공식 코드SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
https://github.com/xzhang00/qstr
공식 코드A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation
https://github.com/xzy-xzy/spor
공식 코드https://github.com/y-d-wang/rsadapter
공식 코드RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering
https://github.com/yafuly/deepfaketextdetect
공식 코드https://github.com/yafuly/mage
공식 코드https://github.com/yafuly/syntacticgen
공식 코드https://github.com/yale-lily/ascle
공식 코드Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation
https://github.com/yale-lily/loft
공식 코드LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control
https://github.com/yale-lily/medgen
공식 코드Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation
https://github.com/yale-lily/r2d2
공식 코드https://github.com/yale-lily/reastap
공식 코드ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples
https://github.com/yale-nlp/bay-calibration-llm-evaluators
공식 코드Bayesian Calibration of Win Rate Estimation with LLM Evaluators
https://github.com/yale-nlp/code-llm-contamination
공식 코드Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models
https://github.com/yale-nlp/llm-t2t
공식 코드https://github.com/yale-nlp/odsum
공식 코드ODSum: New Benchmarks for Open Domain Multi-Document Summarization
https://github.com/yale-nlp/qtsumm
공식 코드https://github.com/yandex-research/specexec
공식 코드SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices
https://github.com/yangbang18/zeronlg
공식 코드https://github.com/yangcong356/bita
공식 코드Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning
https://github.com/yangkevin2/naacl-2021-fudge-controlled-generation
공식 코드FUDGE: Controlled Text Generation With Future Discriminators
https://github.com/yangliuy/HybridNCM
공식 코드https://github.com/yangrui2015/generalizable-reward-model
공식 코드Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
https://github.com/yanguojun123/medical-dialogue
공식 코드ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues
https://github.com/yanlingpan/chatgpt_sentiment
공식 코드Public Attitudes Toward ChatGPT on Twitter: Sentiments, Topics, and Occupations
https://github.com/yannikkellerde/BERT-Defense
공식 코드https://github.com/yanzhang92/LDGCNs
공식 코드Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation
https://github.com/yanzhaoshi/mepnet
공식 코드MEPNet: Medical Entity-balanced Prompting Network for Brain CT Report Generation
https://github.com/yanzhuguo/linguistic-diversity
공식 코드The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text
https://github.com/yanzhuguo/llm-diversity
공식 코드https://github.com/yaolu/Multi-XScience
공식 코드https://github.com/yaserkl/RLSeq2Seq
공식 코드https://github.com/ychen-stat-ml/kernel-adapters
공식 코드https://github.com/yecanlee/decoding-decoded
공식 코드Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.