https://github.com/nachotp/BertCommentSum
공식 코드Neural Abstractive Unsupervised Summarization of Online News Discussions
Papers with Code 아카이브
Abstractive Text Summarization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 20
- 보존된 평가 기록
- 98
Abstractive Text Summarization is the task of generating a short and concise summary that captures the salient ideas of the source text. The generated summaries potentially contain new phrases and sentences that may not appear in the source text.
Source: Generative Adversarial Network for Abstractive Text Summarization
Image credit: Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/naver/gdc
공식 코드Controlling Conditional Language Models without Catastrophic Forgetting
https://github.com/nc0der/greekt5
공식 코드GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization
https://github.com/neulab/guided_summarization
공식 코드GSum: A General Framework for Guided Neural Abstractive Summarization
https://github.com/ng-j-p/rouge-we
공식 코드Better Summarization Evaluation with Word Embeddings for ROUGE
https://github.com/ninikolov/low_resource_summarization
공식 코드https://github.com/ninikolov/summary-denoising
공식 코드https://github.com/njunlp/cop
공식 코드CoP: Factual Inconsistency Detection by Controlling the Preference
https://github.com/nlp-titech/headline-entailment
공식 코드https://github.com/nlp2ct/temposum
공식 코드Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization
https://github.com/nlpyang/PreSumm
공식 코드https://github.com/ntunlp/middlesum
공식 코드On Context Utilization in Summarization with Large Language Models
https://github.com/ntunlp/summafusion
공식 코드https://github.com/ntunlp/summareranker
공식 코드SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization
https://github.com/ntunlp/summscore
공식 코드https://github.com/ntunlp/summscore-acl-findings-2023
공식 코드https://github.com/ntunlplab/fecs
공식 코드https://github.com/nusnlp/reacts
공식 코드Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance
https://github.com/odelliab/HowSumm
공식 코드HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles
https://github.com/pittisl/greentrainer
공식 코드Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
https://github.com/plm3332/fizz
공식 코드FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document
https://github.com/pluslabnlp/amrfact
공식 코드AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation
https://github.com/pluslabnlp/cdm
공식 코드Open-Domain Text Evaluation via Contrastive Distribution Methods
https://github.com/potsawee/longsum0
공식 코드Long-Span Summarization via Local Attention and Content Selection
https://github.com/pranavajitnair/dapa
공식 코드Domain Aligned Prefix Averaging for Domain Generalization in Abstractive Summarization
https://github.com/priberam/s2tsumm
공식 코드https://github.com/priberam/summebr
공식 코드Improving abstractive summarization with energy-based re-ranking
https://github.com/psunlpgroup/fairsumm
공식 코드https://github.com/psunlpgroup/summ-n
공식 코드Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents
https://github.com/pytorch/fairseq
공식 코드Classical Structured Prediction Losses for Sequence to Sequence Learning
https://github.com/pytorch/fairseq/tree/master/examples/rxf
공식 코드https://github.com/qqplot/dcpmi
공식 코드Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
https://github.com/question406/learningtofocus
공식 코드Controlling the Focus of Pretrained Language Generation Models
https://github.com/recitalAI/summa-qa
공식 코드Answers Unite! Unsupervised Metrics for Reinforced Summarization Models
https://github.com/rktamplayo/DenoiseSum
공식 코드Unsupervised Opinion Summarization with Noising and Denoising
https://github.com/rktamplayo/Entity2Topic
공식 코드Entity Commonsense Representation for Neural Abstractive Summarization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.