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/arklyg/sentree
공식 코드https://github.com/arminazizi98/lamda
공식 코드LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation
https://github.com/arnozwang/esports-data-to-text
공식 코드Commentary Generation from Data Records of Multiplayer Strategy Esports Game
https://github.com/arshiyaaggarwal/robust-nlg-bias-eval
공식 코드Towards Robust NLG Bias Evaluation with Syntactically-diverse Prompts
https://github.com/asaakyan/explain-st
공식 코드ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer
https://github.com/asahi-research/script-for-transformer-based-seq2bf
공식 코드https://github.com/asappresearch/constrained-dialogue-generation
공식 코드Long-term Control for Dialogue Generation: Methods and Evaluation
https://github.com/asappresearch/imitkd
공식 코드Autoregressive Knowledge Distillation through Imitation Learning
https://github.com/ashaba1in/smoothie
공식 코드Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation
https://github.com/ashwinkalyan/dbs
공식 코드Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/asinghcsu/agenticrag-survey
공식 코드Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
https://github.com/assafbk/mocha_code
공식 코드https://github.com/astonzhang/Parameterization-of-Hypercomplex-Multiplications
공식 코드https://github.com/asyml/texar
공식 코드Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
https://github.com/atrewin/pgen
공식 코드Scaling Back-Translation with Domain Text Generation for Sign Language Gloss Translation
https://github.com/atrewin/signxmda
공식 코드Cross-modality Data Augmentation for End-to-End Sign Language Translation
https://github.com/atulkum/pointer_summarizer
공식 코드Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View
https://github.com/aub-mind/Arabic-Empathetic-Chatbot
공식 코드Empathetic BERT2BERT Conversational Model: Learning Arabic Language Generation with Little Data
https://github.com/aub-mind/araBERT
공식 코드AraGPT2: Pre-Trained Transformer for Arabic Language Generation
https://github.com/autextification/AuTexTification-Overview
공식 코드https://github.com/automl/llms_feature_engineering_bias
공식 코드Large Language Models Engineer Too Many Simple Features For Tabular Data
https://github.com/aviclu/peekacross
공식 코드Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering
https://github.com/avinashsai/slot-gpt
공식 코드A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System
https://github.com/ba1jun/model-selection-nlp
공식 코드https://github.com/baaivision/emu
공식 코드https://github.com/balhafni/personalized-gen
공식 코드Personalized Text Generation with Fine-Grained Linguistic Control
https://github.com/banerjeepragyan/CAFIE
공식 코드All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation
https://github.com/bangliu/ACS-QG
공식 코드Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus
https://github.com/baoguangsheng/nat-on-doc
공식 코드https://github.com/baoy-nlp/CNAT
공식 코드Non-Autoregressive Translation by Learning Target Categorical Codes
https://github.com/baoy-nlp/DSS-VAE
공식 코드Generating Sentences from Disentangled Syntactic and Semantic Spaces
https://github.com/baoy-nlp/latent-glat
공식 코드$\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation
https://github.com/bastienvanderplaetse/gan-image-captioning
공식 코드https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets
공식 코드Biomedical Data-to-Text Generation via Fine-Tuning Transformers
https://github.com/bboylyg/backdoorllm
공식 코드BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.