https://github.com/ThomasScialom/QuestEval
공식 코드Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation
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/Tiiiger/bert_score
공식 코드https://github.com/TracyGuo2001/NLoRA
공식 코드NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models
https://github.com/TurkuNLP/bert-eval
공식 코드https://github.com/UBC-NLP/araT5
공식 코드AraT5: Text-to-Text Transformers for Arabic Language Generation
https://github.com/UFAL-DSG/tgen
공식 코드A Context-aware Natural Language Generator for Dialogue Systems
https://github.com/UKPLab/SciGen
공식 코드Learning to Reason for Text Generation from Scientific Tables
https://github.com/UKPLab/acl2024-citation-text-generation
공식 코드Systematic Task Exploration with LLMs: A Study in Citation Text Generation
https://github.com/UKPLab/emnlp2017-cmapsum-corpus
공식 코드Bringing Structure into Summaries: Crowdsourcing a Benchmark Corpus of Concept Maps
https://github.com/UKPLab/emnlp2019-dualgraph
공식 코드Enhancing AMR-to-Text Generation with Dual Graph Representations
https://github.com/UKPLab/kg2text
공식 코드Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs
https://github.com/UKPLab/llm_classifier
공식 코드https://github.com/UKPLab/plms-graph2text
공식 코드Investigating Pretrained Language Models for Graph-to-Text Generation
https://github.com/UKPLab/refresh2018-predicting-trends-from-arxiv
공식 코드https://github.com/USArmyResearchLab/ARL-Creative-Visual-Storytelling
공식 코드Envisioning Narrative Intelligence: A Creative Visual Storytelling Anthology
https://github.com/VegB/Text_Infilling
공식 코드https://github.com/VictorProkhorov/KL_Text_VAE
공식 코드https://github.com/VidhushiniSrinivasan16/ICMLA
공식 코드Natural Language Generation Using Reinforcement Learning with External Rewards
https://github.com/VisualJoyce/Transformers4IME
공식 코드https://github.com/WANGBohaO-jpg/MSL
공식 코드MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender
https://github.com/WHUIR/PPVAE
공식 코드Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders
https://github.com/Walleclipse/AGPC
공식 코드Automatic Generation of Personalized Comment Based on User Profile
https://github.com/WangXFng/ELMRec
공식 코드Enhancing High-order Interaction Awareness in LLM-based Recommender Model
https://github.com/WangXinglin/FSC
공식 코드https://github.com/WanzhengZhu/GPS
공식 코드Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech
https://github.com/WanzhengZhu/GRUEN
공식 코드https://github.com/WolfNiu/AutoAugDialogue
공식 코드Automatically Learning Data Augmentation Policies for Dialogue Tasks
https://github.com/WorkInTheDark/FairytaleQA_QAG_System
공식 코드It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books
https://github.com/X-F-Cui/FrameNet-Conditional-Generation
공식 코드Annotating FrameNet via Structure-Conditioned Language Generation
https://github.com/X-PLUG/WritingBench
공식 코드WritingBench: A Comprehensive Benchmark for Generative Writing
https://github.com/XiangLi1999/PosteriorControl-NLG
공식 코드https://github.com/XiangLi1999/PrefixTuning
공식 코드https://github.com/Xiaomeng-Yang/IPAD
공식 코드IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition
https://github.com/XiaoxiaoGuo/rcdqn
공식 코드https://github.com/XinnuoXu/AugNLG
공식 코드AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation
https://github.com/YYF-Tommy/GlobeSumm
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.