Papers with Code 아카이브
Multi-Document Summarization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 5
- 보존된 평가 기록
- 10
Multi-Document Summarization is a process of representing a set of documents with a short piece of text by capturing the relevant information and filtering out the redundant information. Two prominent approaches to Multi-Document Summarization are extractive and abstractive summarization. Extractive summarization systems aim to extract salient snippets, sentences or passages from documents, while abstractive summarization systems aim to concisely paraphrase the content of the documents.
Source: Multi-Document Summarization using Distributed Bag-of-Words Model
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ucfnlp/summarization-sing-pair-mix
공식 코드Scoring Sentence Singletons and Pairs for Abstractive Summarization
https://github.com/webis-de/scolia25-xsum
공식 코드Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization
https://github.com/xinnuoxu/miranews
공식 코드MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization
https://github.com/yale-nlp/odsum
공식 코드ODSum: New Benchmarks for Open Domain Multi-Document Summarization
https://github.com/yaolu/Multi-XScience
공식 코드https://github.com/yeliu918/hetformer
공식 코드HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization
https://github.com/yema2018/attention-aware
공식 코드Global-aware Beam Search for Neural Abstractive Summarization
https://github.com/yema2018/global_aware
공식 코드Global-aware Beam Search for Neural Abstractive Summarization
https://github.com/yg211/acl20-ref-free-eval
공식 코드SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization
https://github.com/yunzhusong/NAACL2022-REFLECT
공식 코드Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-Awareness
https://github.com/DanielaStep/SC
Scoring Sentence Singletons and Pairs for Abstractive Summarization
https://github.com/DanielaStep/sentence_similarity_rouge
Scoring Sentence Singletons and Pairs for Abstractive Summarization
https://github.com/MindSpore-scientific-2/code-14/tree/main/longt5
LongT5: Efficient Text-To-Text Transformer for Long Sequences
https://github.com/W4ngatang/qags
https://github.com/Zefty/rag-end2end-retriever
https://github.com/allenai/mslr-shared-task
https://github.com/allenai/open-mds
PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization
https://github.com/arnelochner/GBTBMDS
Leveraging Graph to Improve Abstractive Multi-Document Summarization
https://github.com/aseidelo/wiki_generator
https://github.com/brsarah20/Alphafold2
https://github.com/bwallace/RCT-summarization-data
https://github.com/denisewong1/ASX300
Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
https://github.com/ibm/kpa_2021_shared_task
Quantitative Argument Summarization and Beyond: Cross-Domain Key Point Analysis
https://github.com/j40903272/bottom-up-summary
https://github.com/lucidrains/marge-pytorch
https://github.com/lucidrains/memory-compressed-attention
https://github.com/manavkapadnis/enigma_argmining
Quantitative Argument Summarization and Beyond: Cross-Domain Key Point Analysis
https://github.com/mythicalhacker/Text-Summarization
https://github.com/prashanth41/text-summarization
https://github.com/pwc-1/Paper-9/tree/main/longformer
PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization
https://github.com/pwc-1/Paper-9/tree/main/longt5
LongT5: Efficient Text-To-Text Transformer for Long Sequences
https://github.com/smartschat/tilse
A Temporally Sensitive Submodularity Framework for Timeline Summarization
https://github.com/utsjiyaoli/qa-attack
LongT5: Efficient Text-To-Text Transformer for Long Sequences
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.