https://github.com/yixinL7/SimCLS
공식 코드SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization
Papers with Code 아카이브
Abstractive Text Summarization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 20
- 보존된 평가 기록
- 98
Abstractive Text Summarization is the task of generating a short and concise summary that captures the salient ideas of the source text. The generated summaries potentially contain new phrases and sentences that may not appear in the source text.
Source: Generative Adversarial Network for Abstractive Text Summarization
Image credit: Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/yixinl7/brio
공식 코드https://github.com/yixinl7/pagesum
공식 코드https://github.com/yuhui-zh15/FactCCX
공식 코드Evaluating the Factual Consistency of Abstractive Text Summarization
https://github.com/yzjiao/Open-vocabulary-event-extraction
공식 코드https://github.com/zhangshiyue/extractive_is_not_faithful
공식 코드https://github.com/zhengkid/eit-enhanced-interactive-transformer
공식 코드https://github.com/zhengkid/partialformer
공식 코드PartialFormer: Modeling Part Instead of Whole for Machine Translation
https://github.com/zhenzhel/coba
공식 코드Correction with Backtracking Reduces Hallucination in Summarization
https://github.com/zhuyunqi96/ngramObj
공식 코드Differentiable N-gram Objective on Abstractive Summarization
https://github.com/zju-daily/aistorian
공식 코드AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation
https://github.com/zsquaredz/Herman
공식 코드Reducing Quantity Hallucinations in Abstractive Summarization
https://github.com/zsquaredz/adapt_vs_finetune
공식 코드To Adapt or to Fine-tune: A Case Study on Abstractive Summarization
https://huggingface.co/facebook/muppet-roberta-base
공식 코드Muppet: Massive Multi-task Representations with Pre-Finetuning
https://huggingface.co/facebook/muppet-roberta-large
공식 코드Muppet: Massive Multi-task Representations with Pre-Finetuning
https://github.com/04RR/SOTA-Vision
https://github.com/10-zin/Synthesizer
Synthesizer: Rethinking Self-Attention in Transformer Models
https://github.com/1wy/bert
https://github.com/2023-MindSpore-1/ms-code-14/tree/main/Transformer
https://github.com/2023-MindSpore-1/ms-code-149
https://github.com/2023-MindSpore-1/ms-code-164
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
https://github.com/2023-MindSpore-1/ms-code-17/tree/main/CLIFF
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization
https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/t5
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
https://github.com/2023-MindSpore-4/Code8/tree/main/AttentionCluster
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/audio_spectrogram_transformer
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/bart
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/bartpho
BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese
https://github.com/2miatran/Natural-Language-Processing
https://github.com/AIKevin/Pointer_Generator_Summarizer
Get To The Point: Summarization with Pointer-Generator Networks
https://github.com/AlCorreia/FABIR
https://github.com/AlexGidiotis/DANCER-summ
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
https://github.com/Amy-1114/transformer
https://github.com/AndreiMoraru123/Neural-Machine-Translation
https://github.com/Andrey885/Machine_translation_PyTorch
https://github.com/AndreyKolomiets/News_Headline_Generation
Get To The Point: Summarization with Pointer-Generator Networks
https://github.com/ArdalanM/nlp-benchmarks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.