https://github.com/martiansideofthemoon/rankgen
공식 코드RankGen: Improving Text Generation with Large Ranking Models
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/martiansideofthemoon/style-transfer-paraphrase
공식 코드Reformulating Unsupervised Style Transfer as Paraphrase Generation
https://github.com/maruker/vec2sent
공식 코드Vec2Sent: Probing Sentence Embeddings with Natural Language Generation
https://github.com/maszhongming/unieval
공식 코드Towards a Unified Multi-Dimensional Evaluator for Text Generation
https://github.com/mataney/APES
공식 코드Question Answering as an Automatic Evaluation Metric for News Article Summarization
https://github.com/mataney/APES-optimizer
공식 코드Question Answering as an Automatic Evaluation Metric for News Article Summarization
https://github.com/matejulcar/slot5-tools
공식 코드Sequence to sequence pretraining for a less-resourced Slovenian language
https://github.com/mathieurita/llm_demonstration_guided_rl
공식 코드Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning
https://github.com/mattf1n/basis-aware-threshold
공식 코드https://github.com/matthewcym/adveval
공식 코드https://github.com/maxattezekbayev/alpha-relu
공식 코드https://github.com/maximek3/e-ViL
공식 코드e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks
https://github.com/maxlchen/controllable-mixed-initiative-dialogue-generation
공식 코드Controllable Mixed-Initiative Dialogue Generation through Prompting
https://github.com/mayer123/udt-qa
공식 코드Open Domain Question Answering with A Unified Knowledge Interface
https://github.com/mc-lan/text4seg
공식 코드https://github.com/mdrafiqulrabin/CI-Memorization
공식 코드Memorization and Generalization in Neural Code Intelligence Models
https://github.com/mdtux89/OpenNMT-py
공식 코드https://github.com/mdtux89/OpenNMT-py-AMR-to-text
공식 코드https://github.com/mebymeby/pseudonymization-framework
공식 코드https://github.com/mediatechnologycenter/spider
공식 코드https://github.com/meetdavidwan/generationprograms
공식 코드GenerationPrograms: Fine-grained Attribution with Executable Programs
https://github.com/meetdavidwan/histalign
공식 코드HistAlign: Improving Context Dependency in Language Generation by Aligning with History
https://github.com/meg-tong/sycophancy-eval
공식 코드https://github.com/megagonlabs/ambignlg
공식 코드https://github.com/megagonlabs/autotemplate
공식 코드AutoTemplate: A Simple Recipe for Lexically Constrained Text Generation
https://github.com/megagonlabs/hallucination_mds
공식 코드From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization
https://github.com/megagonlabs/llm-longeval
공식 코드https://github.com/megagonlabs/nlp4hr-survey
공식 코드https://github.com/mehedihasanbijoy/DPCSpell
공식 코드https://github.com/menggehe/DRAW
공식 코드https://github.com/merterm/cosmic
공식 코드COSMic: A Coherence-Aware Generation Metric for Image Descriptions
https://github.com/merterm/modeling-intensification-for-slg
공식 코드Modeling Intensification for Sign Language Generation: A Computational Approach
https://github.com/meta-diffub/meta-diffub
공식 코드Meta-DiffuB: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration
https://github.com/meta-inf/suq-nlg
공식 코드On Subjective Uncertainty Quantification and Calibration in Natural Language Generation
https://github.com/metaphors/TSAttack
공식 코드TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
https://github.com/mfurkanilaslan/vg-tvp
공식 코드VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.