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/salesforce/diversesumm
공식 코드https://github.com/salesforce/hydra-sum
공식 코드HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models
https://github.com/salesforce/qafacteval
공식 코드QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization
https://github.com/salomeeeee/subsumm
공식 코드Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets
https://github.com/saxenarohit/moviesum
공식 코드MovieSum: An Abstractive Summarization Dataset for Movie Screenplays
https://github.com/saxenarohit/select_summ
공식 코드Select and Summarize: Scene Saliency for Movie Script Summarization
https://github.com/sayarghoshroy/Summaformers
공식 코드https://github.com/scsmuhio/summarization
공식 코드GAE-ISumm: Unsupervised Graph-Based Summarization of Indian Languages
https://github.com/seanie12/CLAPS
공식 코드Contrastive Learning with Adversarial Perturbations for Conditional Text Generation
https://github.com/seasonyao/learnfromhumanedit
공식 코드https://github.com/sebastianGehrmann/bottom-up-summary
공식 코드https://github.com/seongminp/graph-dialogue-summary
공식 코드Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion
https://github.com/shafnehal/samcares
공식 코드https://github.com/shaojintian/power_law_decay
공식 코드https://github.com/shark-nlp/cont
공식 코드https://github.com/shashiongithub/Refresh
공식 코드Ranking Sentences for Extractive Summarization with Reinforcement Learning
https://github.com/shashiongithub/XSum
공식 코드https://github.com/shashiongithub/sidenet
공식 코드https://github.com/sheffieldnlp/AMR2Text-summ
공식 코드https://github.com/shen-chenhui/mred
공식 코드MReD: A Meta-Review Dataset for Structure-Controllable Text Generation
https://github.com/shengqiang-zhang/plate
공식 코드Attention Temperature Matters in Abstractive Summarization Distillation
https://github.com/shentao-yang/preference_grounded_guidance
공식 코드Preference-grounded Token-level Guidance for Language Model Fine-tuning
https://github.com/shichaosun/conabssum
공식 코드Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization
https://github.com/shumingma/SRB
공식 코드A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification
https://github.com/smartmediaai/personalsum
공식 코드PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models
https://github.com/smartyfh/MultiWOZ2.4
공식 코드https://github.com/snowflakedb/ArcticTraining
공식 코드Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences
https://github.com/sobamchan/aclsum
공식 코드ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications
https://github.com/sobamchan/xscitldr
공식 코드X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents
https://github.com/som-shahlab/clinfo.ai
공식 코드https://github.com/sosuperic/MeanSum
공식 코드MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization
https://github.com/spcl/checkembed
공식 코드CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks
https://github.com/ssm123ssm/docgpt-pharm
공식 코드https://github.com/stanfordmimi/clin-summ
공식 코드Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization
https://github.com/stangelid/oposum
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.