gen-ext
: Extractive Summarizationgen-abs
: Abstractive Summarizationgen-2stage
Two-stage Summarization (compressive, hybrid)
regr-auto
: Autoregressive Decoder (Pointer network)regr-nonauto
: Non-autoregressive Decoder (Sequence labeling)
task-singleDoc
: Single-document Summarizationtask-multiDoc
: Multi-document Summarizationtask-senCompre:
Sentence Compressiontask-sci
: Scientific Papertask-radiologyReport
: Radiology Reportstask-multimodal
: Multi-modal Summarizationtask-aspect
: Aspect-based Summarizationtask-opinion
: Opinion Summarizationtask-review
: Review Summarizationtask-meeting
: Meeting-based Summarizationtask-conversation
: Consersation-based Summarizationtask-medical
: Medical text-related Summarizationtask-covid
: COVID-19 related Summarizationtask-query
: query-based Summarizationtask-question
: question-based Summarizationtask-video
: Video-based Summarizationtask-code
: Source Code Summarizationtask-control
: Controllable Summarizationtask-event
: Event-based Summarizationtask-longtext
: Summarization for Long Texttask-knowledge
: Text Summarization with External Knowledgetask-highlight
: Pick out important content and emphasizetask-analysis
: Model Understanding or Interpretabilitytask-novel
: Novel Chapter Generationtask-argument
: Automatic Argument Summarization
arch-rnn
: Recurrent Neural Networks (LSTM, GRU)arch-cnn
: Convolutional Neural Networks (CNN)arch-transformer
: Transformerarch-graph
: Graph Neural Networks or Statistic Graph Modelsarch-gnn
: Graph Neural Networksarch-textrank
: TextRankarch-att
: Attention Mechanismarch-pointer
: Pointer Layerarch-coverage
: Coverage Mechanism
train-sup
: Supervised Learningtrain-unsup
: Unsupervised Learningtrain-weak
: (impliestrain-sup
): Weakly Supervised Learningtrain-multitask
: Multi-task Learningtrain-multilingual
: Multi-lingual Learningtrain-multimodal
: Multi-modal Learningtrain-auxiliary
: Joint Trainingtrain-transfer
: Cross-domain Learning, Transfer Learning, Domain Adaptationtrain-active
: Active Learning, Boostrappingtrain-adver
: Adversarial Learningtrain-template
: Template-based Summarizationtrain-augment
: Data Augmentationtrain-curriculum
: Curriculum Learningtrain-lowresource
: Low-resource Summarizationtrain-retrieval
: Retrieval-based Summarizationtrain-meta
: Meta-learning
pre-word2vec
: word2vecpre-glove
: GLoVepre-bert
: BERTpre-elmo
: ELMopre-hibert
: HiBERTpre-bart
: BARTpre-pegasus
: PEGASUSpre-unilm
: UNILMpre-mass
: MASSpre-T5
: Text-to-Text Transfer Transformerpre-S2ORC
: Pretrained model on semantic scholar open research corpuspre-sciBERT
: Scientific paper based pre-trained modelpre-SPECTER
: Scientific Paper Embeddings using Citationinformed TransformERs
nondif-straightthrough
: Straight-through Estimatornondif-gumbelsoftmax
: Gumbel Softmaxnondif-minrisk
: Minimum Risk Trainingnondif-reinforce
: REINFORCE
adv-gan
: Generative Adversarial Networksadv-feat
: Adversarial Feature Learningadv-examp
: Adversarial Examplesadv-train
: Adversarial Training
latent-vae
: Variational Auto-encoderlatent-topic
: Topic Model
data-new
: Constructing a new datasetdata-annotation
: Annotation Methodology
eval-human
: Human Evaluationeval-metric-rouge
: ROUGEeval-metric-bertscore
: BERTScoreeval-aspect-coherence
: Coherenceeval-aspect-redundancy
: Redundancy of Summaryeval-aspect-factuality
: Factualityeval-aspect-abstractness
: Abstractnesseval-referenceQuality
: Reference Qualityeval-metric-learnable
: Metrics are Learnableeval-optimize-humanJudgement
: Optimization towards human judgementeval-reference-less
: Reference-less Approach to Automatic Evaluationeval-metric-unsupervised
: Unsupervised Automatic Evaluation
survey-2020
: A survey paper in 2020