https://github.com/FiscalNote/BillSum
공식 코드BillSum: A Corpus for Automatic Summarization of US Legislation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
BillSum: A Corpus for Automatic Summarization of US Legislation
Deep Learning Based Multi-Label Text Classification of UNGA Resolutions
PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction
Continual Learning for Text Classification with Information Disentanglement Based Regularization
Local Additivity Based Data Augmentation for Semi-supervised NER
BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model
Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks
Integrating Local Context and Global Cohesiveness for Open Information Extraction
A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data
Improving the Transformer Translation Model with Document-Level Context
Contrastive Learning and Mixture of Experts Enables Precise Vector Embeddings
Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences
What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation
Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues
Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data
ICECAP: Information Concentrated Entity-aware Image Captioning
Fine-Grained Image Captioning with Global-Local Discriminative Objective
LTP: A New Active Learning Strategy for CRF-Based Named Entity Recognition
Exploring Discourse Structures for Argument Impact Classification
Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model
Multi-hop Question Generation with Graph Convolutional Network
Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.