https://github.com/jacob-parnell-rozetta/longformer_coverage
공식 코드A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization
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/jiacheng-xu/lattice-generation
공식 코드https://github.com/jiacheng-xu/neu-compression-sum
공식 코드Neural Extractive Text Summarization with Syntactic Compression
https://github.com/jonas-becker/text-generation
공식 코드Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges
https://github.com/jpeper/pelms
공식 코드PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization
https://github.com/julmaxi/summary_bias
공식 코드https://github.com/kepingbi/ARedSumSentRank
공식 코드AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization
https://github.com/knot-fit-but/oapapers
공식 코드https://github.com/knot-fit-but/oapapersviewer
공식 코드https://github.com/law-ai/summarization
공식 코드Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation
https://github.com/leehaoyuan/coverage_fairness
공식 코드https://github.com/liatschiff/openasp
공식 코드OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarization
https://github.com/lioutasb/TaLKConvolutions
공식 코드https://github.com/lliangchenc/DeepChannel
공식 코드DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
https://github.com/lovodkin93/attribute-first-then-generate
공식 코드Attribute First, then Generate: Locally-attributable Grounded Text Generation
https://github.com/lukecq1231/nats
공식 코드Distraction-Based Neural Networks for Document Summarization
https://github.com/lumia-group/fouriertransformer
공식 코드Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator
https://github.com/luyang-huang96/LongDocSum
공식 코드https://github.com/manavkapadnis/legalevaluation_lrec2022
공식 코드https://github.com/maszhongming/MatchSum
공식 코드https://github.com/mediatechnologycenter/spider
공식 코드https://github.com/meetdavidwan/faithful-multimodal-summ
공식 코드Evaluating and Improving Factuality in Multimodal Abstractive Summarization
https://github.com/meetdavidwan/generationprograms
공식 코드GenerationPrograms: Fine-grained Attribution with Executable Programs
https://github.com/megagonlabs/hallucination_mds
공식 코드From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization
https://github.com/microsoft/comphrdoc
공식 코드https://github.com/microsoft/unilm
공식 코드Unified Language Model Pre-training for Natural Language Understanding and Generation
https://github.com/mingzi151/SummPip
공식 코드SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression
https://github.com/mirzaalimm/truncationvssummarization
공식 코드Investigating Text Shortening Strategy in BERT: Truncation vs Summarization
https://github.com/misonuma/strsum
공식 코드https://github.com/molichenxi/haesum
공식 코드Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level
https://github.com/morningmoni/RL-MMR
공식 코드Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning
https://github.com/mswellhao/PacSum
공식 코드Sentence Centrality Revisited for Unsupervised Summarization
https://github.com/multilexsum/dataset
공식 코드Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities
https://github.com/ninikolov/low_resource_summarization
공식 코드https://github.com/nlpyang/BertSum
공식 코드https://github.com/nlpyang/PreSumm
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.