https://github.com/calclavia/story-generation
공식 코드Improving Neural Story Generation by Targeted Common Sense Grounding
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/cambridgeltl/zepo
공식 코드Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments
https://github.com/caoyu-noob/Multi-GPT2
공식 코드Pretrained Language Models for Dialogue Generation with Multiple Input Sources
https://github.com/caoyu-noob/d3
공식 코드A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation
https://github.com/caoyu-noob/embedding_augmentation
공식 코드Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation
https://github.com/carolinazheng/invariant-control-gen
공식 코드An Invariant Learning Characterization of Controlled Text Generation
https://github.com/carriex/lfqa_eval
공식 코드A Critical Evaluation of Evaluations for Long-form Question Answering
https://github.com/casszhao/reagent
공식 코드ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models
https://github.com/causalate-mitigates-bias/causal-ate-mitigates-bias
공식 코드Causal ATE Mitigates Unintended Bias in Controlled Text Generation
https://github.com/cbellinger27/learning-when-to-observe-in-rl
공식 코드Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning
https://github.com/cbjuan/tokenizers-neural-nets-2020-paper
공식 코드https://github.com/cdhx/qdtqa
공식 코드Question Decomposition Tree for Answering Complex Questions over Knowledge Bases
https://github.com/cdjhz/discodvt
공식 코드DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer
https://github.com/cdjhz/multigen
공식 코드Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph
https://github.com/cesare-spinoso/rsasumm-customnlp4u
공식 코드https://github.com/chanchimin/chateval
공식 코드ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
https://github.com/changyuchen347/semi-offline-rl
공식 코드Semi-Offline Reinforcement Learning for Optimized Text Generation
https://github.com/chanliang/orig
공식 코드Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization
https://github.com/chaojiang06/neural-Jacana
공식 코드https://github.com/chaos96/fourierft
공식 코드Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
https://github.com/chaoyitud/dual-watermarks
공식 코드https://github.com/chauncey-jheng/pcrl-mrg
공식 코드https://github.com/chengfeng-dou/sptesting
공식 코드https://github.com/chenmeiqii/teach-llm-lr
공식 코드Improving Large Language Models in Event Relation Logical Prediction
https://github.com/chenrj233/lmedr
공식 코드Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues
https://github.com/chenxu05037/COSPLAY
공식 코드COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas
https://github.com/chicagohai/hypoeval-gen
공식 코드HypoEval: Hypothesis-Guided Evaluation for Natural Language Generation
https://github.com/chin-gyou/Div-Non-Conv
공식 코드Diversifying Dialogue Generation with Non-Conversational Text
https://github.com/chin-gyou/controllable-selection
공식 코드Select and Attend: Towards Controllable Content Selection in Text Generation
https://github.com/chongyangtao/LLMs-for-NLG-Evaluation
공식 코드Leveraging Large Language Models for NLG Evaluation: Advances and Challenges
https://github.com/chorlinglau/poetrydiffusion
공식 코드PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation
https://github.com/chrisdonahue/ilm
공식 코드https://github.com/chrishokamp/dynamic-transformer-ensembles
공식 코드DynE: Dynamic Ensemble Decoding for Multi-Document Summarization
https://github.com/chtmp223/suri
공식 코드Suri: Multi-constraint Instruction Following for Long-form Text Generation
https://github.com/chujiezheng/click
공식 코드Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning
https://github.com/cimeister/typical-sampling
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.