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/bondarchukb/PEGASUS
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
https://github.com/brainsqueeze/text2vec
https://github.com/brandontrabucco/scaled_dot_product_attention
https://github.com/brightmart/bert_customized
https://github.com/brightmart/bert_original
https://github.com/bshantam97/Attention_Based_Networks
https://github.com/btobab/R-Drop
https://github.com/bunsenfeng/factkb
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics
https://github.com/buschmo/Simple-German-Corpus
https://github.com/bwallace/RCT-summarization-data
https://github.com/bytedance/neurst
https://github.com/bzhangGo/zero
https://github.com/cadia-lvl/fastspeech2
https://github.com/cahya-wirawan/indonesian-language-models
https://github.com/camlaedtke/NLP
https://github.com/caoyujiALgLM/NLP
https://github.com/caoyujiALgLM/NLP-progress
https://github.com/cccntu/ft5-demo
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
https://github.com/cccntu/ft5-demo-space
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
https://github.com/chakravarthi-v/Polaroid-1
https://github.com/chalothon/BERT_Practice
https://github.com/chandu7077/mybert
https://github.com/chen-xiong-yi/OwnBERT
https://github.com/chengchingwen/transformers.jl
https://github.com/chesterdu/contrastive_summary
https://github.com/chiayewken/bert-qa
https://github.com/chrisleunglokhin/Capstone-BERT
https://github.com/christianspybrook/article_recommender
https://github.com/cliang1453/camero
https://github.com/cloudmcloudyo/capstone
https://github.com/cmsflash/efficient-attention
https://github.com/coco60/bert-test
https://github.com/colorfulscoop/tfdlg
https://github.com/complementizer/news-tls
Examining the State-of-the-Art in News Timeline Summarization
https://github.com/conceptofmind/LaMDA-pytorch
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.