https://github.com/crowddynamicslab/cevlm
공식 코드CEV-LM: Controlled Edit Vector Language Model for Shaping Natural Language Generations
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/crowddynamicslab/styleinfusion
공식 코드Audience-Centric Natural Language Generation via Style Infusion
https://github.com/crseu/llmtime_vs_arima
공식 코드An Evaluation of Standard Statistical Models and LLMs on Time Series Forecasting
https://github.com/csebuetnlp/banglanlg
공식 코드https://github.com/csitfun/logicot
공식 코드https://github.com/csjianyang/ganlm
공식 코드GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator
https://github.com/csm9493/efficient-llm-unlearning
공식 코드Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
https://github.com/cubenlp/FuxiBench
공식 코드https://github.com/cuishiyao96/fft
공식 코드FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity
https://github.com/cw-wan/EmoDynamiX-v2
공식 코드https://github.com/cyberagentailab/adparaphrase
공식 코드https://github.com/cyberagentailab/adtec
공식 코드AdTEC: A Unified Benchmark for Evaluating Text Quality in Search Engine Advertising
https://github.com/cyberagentailab/camera
공식 코드Striking Gold in Advertising: Standardization and Exploration of Ad Text Generation
https://github.com/cyberagentailab/faithcamera
공식 코드FaithCAMERA: Construction of a Faithful Dataset for Ad Text Generation
https://github.com/cyberagentailab/lctg-bench
공식 코드https://github.com/cyberagentailab/mbr-anomaly
공식 코드On the True Distribution Approximation of Minimum Bayes-Risk Decoding
https://github.com/cycloneboy/csc_eda
공식 코드EdaCSC: Two Easy Data Augmentation Methods for Chinese Spelling Correction
https://github.com/cyp-jlu-ai/ba-lora
공식 코드https://github.com/cyr19/menli
공식 코드MENLI: Robust Evaluation Metrics from Natural Language Inference
https://github.com/cyr19/reproducibility
공식 코드https://github.com/cyrilsterling/textgen
공식 코드How Control Information Influences Multilingual Text Image Generation and Editing?
https://github.com/czyssrs/Few-Shot-NLG
공식 코드https://github.com/czyssrs/Logic2Text
공식 코드Logic2Text: High-Fidelity Natural Language Generation from Logical Forms
https://github.com/d-ailin/clip-guided-decoding
공식 코드https://github.com/d-matrix-ai/keyformer-llm
공식 코드Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference
https://github.com/da03/criticize_text_generation
공식 코드https://github.com/dadelani/AfriHG
공식 코드https://github.com/daehuikim/WikiOFGraph
공식 코드https://github.com/daeveraert/gradient-information-optimization
공식 코드GIO: Gradient Information Optimization for Training Dataset Selection
https://github.com/dailenson/one-dm
공식 코드https://github.com/dakuo/haconvgnn
공식 코드https://github.com/damo-nlp-sg/gpt4-as-dataanalyst
공식 코드https://github.com/damo-nlp-sg/hierencdec
공식 코드A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization
https://github.com/damo-nlp-sg/video-llama
공식 코드Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
https://github.com/daniel3303/storyreasoning
공식 코드StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation
https://github.com/danielabweiss/extending-sentence-fusion-resources
공식 코드Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.