Papers with Code 아카이브

Abstractive Text Summarization

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/land-fbk/benchmark-gen-explanations

공식 코드

Benchmarking the Generation of Fact Checking Explanations

https://github.com/law-ai/summarization

공식 코드

Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation

https://github.com/lcs2-iiitd/mtldrgen

공식 코드

Fusing Multimodal Signals on Hyper-complex Space for Extreme Abstractive Text Summarization (TL;DR) of Scientific Contents

https://github.com/lhfazry/spin-summ

공식 코드

A Split-then-Join Approach to Abstractive Summarization for Very Long Documents in a Low Resource Setting

https://github.com/libeineu/ode-transformer

공식 코드

ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation

https://github.com/linto-ai/fredsum

공식 코드

FREDSum: A Dialogue Summarization Corpus for French Political Debates

https://github.com/liyan06/aggrefact

공식 코드

Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors

https://github.com/lumia-group/fouriertransformer

공식 코드

Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator

https://github.com/luyang-huang96/GraphAugmentedSum

공식 코드

Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward

https://github.com/maarten-deraedt/idas-intent-discovery-with-abstract-summarization

공식 코드

IDAS: Intent Discovery with Abstractive Summarization

https://github.com/machelreid/subformer

공식 코드

Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers

https://github.com/makcedward/nlpaug

공식 코드

CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization

https://github.com/maszhongming/granuduc

공식 코드

Unsupervised Multi-Granularity Summarization

https://github.com/mcao516/entfa

공식 코드

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization

https://github.com/mcao516/rej-summ

공식 코드

Learning with Rejection for Abstractive Text Summarization

https://github.com/mcao610/Factual-Error-Correction

공식 코드

Factual Error Correction for Abstractive Summarization Models

https://github.com/meetdavidwan/factpegasus

공식 코드

FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization

https://github.com/meetdavidwan/faithful-multimodal-summ

공식 코드

Evaluating and Improving Factuality in Multimodal Abstractive Summarization

https://github.com/meetdavidwan/histalign

공식 코드

HistAlign: Improving Context Dependency in Language Generation by Aligning with History

https://github.com/melaniesubbiah/storysumm

공식 코드

STORYSUMM: Evaluating Faithfulness in Story Summarization

https://github.com/microsoft/DeBERTa

공식 코드

Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization

https://github.com/microsoft/DeepSpeed

공식 코드

ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks

https://github.com/microsoft/HMNet

공식 코드

A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining

https://github.com/microsoft/ProphetNet

공식 코드

ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training

https://github.com/microsoft/unilm

공식 코드

Unified Language Model Pre-training for Natural Language Understanding and Generation

https://github.com/microsoft/unilm/tree/master/deltalm

공식 코드

DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders

https://github.com/mingdachen/SummScreen

공식 코드

SummScreen: A Dataset for Abstractive Screenplay Summarization

https://github.com/mingdachen/tvrecap

공식 코드

TVStoryGen: A Dataset for Generating Stories with Character Descriptions

https://github.com/misonuma/recursum

공식 코드

Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance

https://github.com/misonuma/strsum

공식 코드

Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking

https://github.com/mit-han-lab/lite-transformer

공식 코드

Lite Transformer with Long-Short Range Attention

https://github.com/morningmoni/ede

공식 코드

Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation

https://github.com/mr-kenlee/cloze

공식 코드

Just ClozE! A Novel Framework for Evaluating the Factual Consistency Faster in Abstractive Summarization

https://github.com/mr-kenlee/factcloze

공식 코드

Improving Factual Error Correction for Abstractive Summarization via Data Distillation and Conditional-generation Cloze

https://github.com/mukhtar-algezoli/Arabic_PreSumm

공식 코드

BERT Fine-tuning For Arabic Text Summarization

https://github.com/multilexsum/dataset

공식 코드

Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.