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/dialogue-evaluation/ruatd
공식 코드Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in Russian
https://github.com/didi/delta
공식 코드https://github.com/disl-lab/finesure-acl24
공식 코드https://github.com/dmhyun/msrp
공식 코드https://github.com/dmmiller612/lecture-summarizer
공식 코드Leveraging BERT for Extractive Text Summarization on Lectures
https://github.com/dongqi-me/vista
공식 코드What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations
https://github.com/dorinapetra/summarization
공식 코드HunSum-1: an Abstractive Summarization Dataset for Hungarian
https://github.com/dropreg/R-Drop
공식 코드https://github.com/dvlab-research/longlora
공식 코드LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
https://github.com/edoost/perkey
공식 코드Persian Keyphrase Generation Using Sequence-to-Sequence Models
https://github.com/ellenmellon/GraphSum
공식 코드https://github.com/embeddings-benchmark/mteb
공식 코드https://github.com/engsalem/arglegalsumm
공식 코드ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining
https://github.com/engsalem/legalsummreranking
공식 코드Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking
https://github.com/engsalem/reflectsumm
공식 코드ReflectSumm: A Benchmark for Course Reflection Summarization
https://github.com/epfl-dlab/KLearn
공식 코드KLearn: Background Knowledge Inference from Summarization Data
https://github.com/eranhirs/sentence_union_generation
공식 코드Revisiting Sentence Union Generation as a Testbed for Text Consolidation
https://github.com/ernie-research/cd-rlhf
공식 코드https://github.com/ernie-research/ma-rlhf
공식 코드MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
https://github.com/esdurmus/Wikilingua
공식 코드WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization
https://github.com/esdurmus/summary-faithfulness
공식 코드https://github.com/euranova/CASS-dataset
공식 코드STRASS: A Light and Effective Method for Extractive Summarization Based on Sentence Embeddings
https://github.com/evidencebp/comsum
공식 코드ComSum: Commit Messages Summarization and Meaning Preservation
https://github.com/facebookresearch/bart_ls
공식 코드Adapting Pretrained Text-to-Text Models for Long Text Sequences
https://github.com/facebookresearch/vizseq
공식 코드https://github.com/fahmidahossain/Report_Summarization
공식 코드CSTRL: Context-Driven Sequential Transfer Learning for Abstractive Radiology Report Summarization
https://github.com/fajri91/RSTExtractor
공식 코드https://github.com/fajri91/sum_liputan6
공식 코드Liputan6: A Large-scale Indonesian Dataset for Text Summarization
https://github.com/firatcekinel/multi-task-fact-checking
공식 코드Explaining Veracity Predictions with Evidence Summarization: A Multi-Task Model Approach
https://github.com/fkirste/gem_emnlp2022-toasts
공식 코드Analyzing Multi-Task Learning for Abstractive Text Summarization
https://github.com/fladhak/contrastive_error_attribution
공식 코드https://github.com/fladhak/effective-faithfulness
공식 코드https://github.com/flbbb/locost-summarization
공식 코드LOCOST: State-Space Models for Long Document Abstractive Summarization
https://github.com/florianbaud/retrieval-augmented-mds
공식 코드Non-Parametric Memory Guidance for Multi-Document Summarization
https://github.com/forrestbao/suenes
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.