Papers with Code 아카이브
Document Summarization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 7
- 보존된 평가 기록
- 50
Automatic Document Summarization is the task of rewriting a document into its shorter form while still retaining its important content. The most popular two paradigms are extractive approaches and abstractive approaches. Extractive approaches generate summaries by extracting parts of the original document (usually sentences), while abstractive methods may generate new words or phrases which are not in the original document.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/applicaai/pyramidions
공식 코드Sparsifying Transformer Models with Trainable Representation Pooling
https://github.com/ariecattan/multi_mds
공식 코드https://github.com/arvind-balaji/debate-cards
공식 코드DebateSum: A large-scale argument mining and summarization dataset
https://github.com/brxx122/HeterSUMGraph
공식 코드Heterogeneous Graph Neural Networks for Extractive Document Summarization
https://github.com/bzhangGo/zero
공식 코드On Sparsifying Encoder Outputs in Sequence-to-Sequence Models
https://github.com/c-juhwan/multi_news_plus
공식 코드Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation
https://github.com/c-rajan/Multi-source-NewsSummarization
공식 코드Shaping Political Discourse using multi-source News Summarization
https://github.com/cestwc/universal-evasion
공식 코드https://github.com/chatc/summ-n
공식 코드Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents
https://github.com/chrishokamp/dynamic-transformer-ensembles
공식 코드DynE: Dynamic Ensemble Decoding for Multi-Document Summarization
https://github.com/cliveyn/pdsum
공식 코드PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream
https://github.com/clovaai/FocusSeq2Seq
공식 코드https://github.com/complementizer/wcep-mds-dataset
공식 코드A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal
https://github.com/computationalmedia/supmmd
공식 코드SupMMD: A Sentence Importance Model for Extractive Summarization using Maximum Mean Discrepancy
https://github.com/congboma/disentanglesum
공식 코드Disentangling Specificity for Abstractive Multi-document Summarization
https://github.com/congressRA/sample-agent
공식 코드Agent-Enhanced Large Language Models for Researching Political Institutions
https://github.com/craffel/mocha
공식 코드https://github.com/damo-nlp-sg/hierencdec
공식 코드A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization
https://github.com/danielabweiss/extending-sentence-fusion-resources
공식 코드Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations
https://github.com/danielabweiss/qa-align
공식 코드QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions
https://github.com/darsh10/Nutribullets
공식 코드Nutri-bullets: Summarizing Health Studies by Composing Segments
https://github.com/dcdmllm/ideal_summary
공식 코드https://github.com/deepspeedai/deepspeed
공식 코드Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences
https://github.com/eranhirs/sentence_union_generation
공식 코드Revisiting Sentence Union Generation as a Testbed for Text Consolidation
https://github.com/florianbaud/retrieval-augmented-mds
공식 코드Non-Parametric Memory Guidance for Multi-Document Summarization
https://github.com/forrestbao/suenes
공식 코드https://github.com/google-research-datasets/aquamuse
공식 코드AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization
https://github.com/google-research-datasets/xsum_hallucination_annotations
공식 코드https://github.com/google-research/bigbird
공식 코드https://github.com/homealim2012/QE_Mani_Summary
공식 코드Using Query Expansion in Manifold Ranking for Query-Oriented Multi-Document Summarization
https://github.com/hpzhang94/hegel_sum
공식 코드HEGEL: Hypergraph Transformer for Long Document Summarization
https://github.com/huankoh/long-doc-summarization
공식 코드An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics
https://github.com/icannos/glimpse-mds
공식 코드GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews
https://github.com/iriscxy/unified-timeline-summarizer
공식 코드Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order
https://github.com/j-rossi-nl/verbcl
공식 코드VerbCL: A Dataset of Verbatim Quotes for Highlight Extraction in Case Law
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.