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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph
From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization
CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
PublicHearingBR: A Brazilian Portuguese Dataset of Public Hearing Transcripts for Summarization of Long Documents
A Novel LLM-based Two-stage Summarization Approach for Long Dialogues
GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization
L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?
ConServe: Harvesting GPUs for Low-Latency and High-Throughput Large Language Model Serving
Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications
BERT-VBD: Vietnamese Multi-Document Summarization Framework
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
Abstractive Text Summarization: State of the Art, Challenges, and Improvements
SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section
Biomedical Large Languages Models Seem not to be Superior to Generalist Models on Unseen Medical Data
Preference-Guided Reflective Sampling for Aligning Language Models
GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization
MovieSum: An Abstractive Summarization Dataset for Movie Screenplays
SumRecom: A Personalized Summarization Approach by Learning from Users' Feedback
Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency
Rethinking Transformer-based Multi-document Summarization: An Empirical Investigation
IDEAL: Leveraging Infinite and Dynamic Characterizations of Large Language Models for Query-focused Summarization
Proposal Report for the 2nd SciCAP Competition 2024
TocBERT: Medical Document Structure Extraction Using Bidirectional Transformers
LightPAL: Lightweight Passage Retrieval for Open Domain Multi-Document Summarization
GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews
Key-Element-Informed sLLM Tuning for Document Summarization
CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks
The Power of Summary-Source Alignments
Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition
DLAFormer: An End-to-End Transformer For Document Layout Analysis
Thesis: Document Summarization with applications to Keyword extraction and Image Retrieval
Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level
Disentangling Specificity for Abstractive Multi-document Summarization
Understanding Position Bias Effects on Fairness in Social Multi-Document Summarization
OARelatedWork: A Large-Scale Dataset of Related Work Sections with Full-texts from Open Access Sources
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.