Text Summarization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 12
- 평가표
- 37
- 보존된 평가 기록
- 233
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/MJ-Jang/RNN_SVAE
Recurrent Neural Network-Based Semantic Variational Autoencoder for Sequence-to-Sequence Learning
https://github.com/MOHAMEDELDAKDOUKY/bert_adjusted
https://github.com/MS-Mind/MS-Code-01/tree/main/seq2seq
Lossless Acceleration for Seq2seq Generation with Aggressive Decoding
https://github.com/MS-P3/code5/tree/main/gpt2
https://github.com/MS-P3/code5/tree/main/t5
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
https://github.com/MS-P3/code7/tree/main/xlm_prophetnet
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
https://github.com/MaZhiyuanBUAA/bert-tf1.4.0
https://github.com/MachineLearningSystem/25MLSYS-NEO
NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference
https://github.com/ManuMahadevaswamy/PEGASUS
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
https://github.com/Maple728/transformer
https://github.com/MarcBS/keras
https://github.com/MashaKubyshina/learning_ML
https://github.com/Matthewdowney18/Transformer_Dialogue
https://github.com/Maz101/Bert
https://github.com/Maz101/pretrainingdataset
https://github.com/MichaelZhouwang/LMlexsub
https://github.com/Mind23-2/MindCode-132
https://github.com/Mind23-2/MindCode-160
https://github.com/MindCode-4/code-10/tree/main/FDDE/train-fine
https://github.com/MindCode-4/code-11/tree/main/fastformer-additive
https://github.com/MindCode-4/code-2/tree/main/pegasus
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
https://github.com/MindCode-4/code-2/tree/main/pegasus_x
Investigating Efficiently Extending Transformers for Long Input Summarization
https://github.com/MindCode-4/code-5/tree/main/transformer
https://github.com/MindCode-4/code-5/tree/main/xlm_prophetnet
https://github.com/MindCode-4/code-7/tree/main/factorized-attention
https://github.com/MindCode-4/code-7/tree/main/fastformer-additive
https://github.com/MindSpore-paper-code-3/code6/tree/main/CLIFF
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization
https://github.com/MindSpore-paper-code-3/code9/tree/main/mass
MASS: Masked Sequence to Sequence Pre-training for Language Generation
https://github.com/MindSpore-scientific-2/code-12/tree/main/fastformer-additive
https://github.com/MindSpore-scientific-2/code-14/tree/main/longt5
LongT5: Efficient Text-To-Text Transformer for Long Sequences
https://github.com/MindSpore-scientific/code-11/tree/main/Least_Generative
Leveraging Pre-trained Checkpoints for Sequence Generation Tasks
https://github.com/MindSpore-scientific/code-11/tree/main/Translation-Invariant/model
https://github.com/MindSpore-scientific/code-12/tree/main/FDDE/train-fine
https://github.com/MindSpore-scientific/code-6/tree/main/Neural-Side-by-Side
https://github.com/MindSpore-scientific/code-8/tree/main/Translation-Invariant/model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.