https://github.com/10-zin/Synthesizer
Synthesizer: Rethinking Self-Attention in Transformer Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Text Summarization is a natural language processing (NLP) task that involves condensing a lengthy text document into a shorter, more compact version while still retaining the most important information and meaning. The goal is to produce a summary that accurately represents the content of the original text in a concise form.
There are different approaches to text summarization, including extractive methods that identify and extract important sentences or phrases from the text, and abstractive methods that generate new text based on the content of the original text.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Synthesizer: Rethinking Self-Attention in Transformer Models
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
BARThez: a Skilled Pretrained French Sequence-to-Sequence Model
BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese
Get To The Point: Summarization with Pointer-Generator Networks
Get To The Point: Summarization with Pointer-Generator Networks
TextKD-GAN: Text Generation using KnowledgeDistillation and Generative Adversarial Networks
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Get To The Point: Summarization with Pointer-Generator Networks
GLM: General Language Model Pretraining with Autoregressive Blank Infilling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.