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/sjtugzx/akg
공식 코드https://github.com/skangasl/continuous-lm-interpolation
공식 코드Continuous Language Model Interpolation for Dynamic and Controllable Text Generation
https://github.com/skoltech-nlp/sgdd-tst
공식 코드Studying the role of named entities for content preservation in text style transfer
https://github.com/skp1999/SMAB
공식 코드https://github.com/skywalker023/focused-empathy
공식 코드Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes
https://github.com/skywalker023/pragmatic-consistency
공식 코드https://github.com/skywalker023/prosocial-dialog
공식 코드ProsocialDialog: A Prosocial Backbone for Conversational Agents
https://github.com/skywalker023/sodaverse
공식 코드SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization
https://github.com/sled-group/driVLMe
공식 코드DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences
https://github.com/smart-lty/parallelspeculativedecoding
공식 코드https://github.com/smartmedia-ai/norglm
공식 코드https://github.com/smith-pit/llm-partisan-bias
공식 코드Whose Side Are You On? Investigating the Political Stance of Large Language Models
https://github.com/snakeztc/NeuralDialog-CVAE
공식 코드https://github.com/snakeztc/NeuralDialog-LAED
공식 코드Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
https://github.com/snakeztc/NeuralDialog-LaRL
공식 코드https://github.com/snakeztc/NeuralDialog-ZSDG
공식 코드Zero-Shot Dialog Generation with Cross-Domain Latent Actions
https://github.com/snakeztc/SimDial
공식 코드Zero-Shot Dialog Generation with Cross-Domain Latent Actions
https://github.com/snipsco/automatic-data-generation
공식 코드Conditioned Query Generation for Task-Oriented Dialogue Systems
https://github.com/songhaoyu/BoB
공식 코드BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
https://github.com/songhaoyu/RCDG
공식 코드Generating Persona Consistent Dialogues by Exploiting Natural Language Inference
https://github.com/songweige/rich-text-to-image
공식 코드https://github.com/sony/talkhier
공식 코드Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems
https://github.com/sophiegroenwold/AAVE_SAE_dataset
공식 코드Investigating African-American Vernacular English in Transformer-Based Text Generation
https://github.com/souro/multilingual_text_detoxification
공식 코드https://github.com/souro/multilingual_tst
공식 코드Multilingual Text Style Transfer: Datasets & Models for Indian Languages
https://github.com/souro/tst_llm
공식 코드Are Large Language Models Actually Good at Text Style Transfer?
https://github.com/spin-umass/stealing-the-decoding-algorithms-of-language-models
공식 코드https://github.com/sprintml/toxicbench
공식 코드Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images
https://github.com/squareslab/varclr
공식 코드VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning
https://github.com/srijankr/petgen
공식 코드PETGEN: Personalized Text Generation Attack on Deep Sequence Embedding-based Classification Models
https://github.com/stanfordnlp/color-describer
공식 코드https://github.com/stanfordnlp/dspy
공식 코드DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
https://github.com/starsuzi/udeg
공식 코드Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation
https://github.com/stas-semeniuta/textvae
공식 코드A Hybrid Convolutional Variational Autoencoder for Text Generation
https://github.com/steffeneger/global-explainability-metrics
공식 코드Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.