https://github.com/yjw1029/deepqse
공식 코드Effective and Efficient Query-aware Snippet Extraction for Web Search
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Effective and Efficient Query-aware Snippet Extraction for Web Search
ALiiCE: Evaluating Positional Fine-grained Citation Generation
Pre-Training a Graph Recurrent Network for Language Representation
A Span-Extraction Dataset for Chinese Machine Reading Comprehension
A Sentence Cloze Dataset for Chinese Machine Reading Comprehension
Improving word mover's distance by leveraging self-attention matrix
Translation Word-Level Auto-Completion: What can we achieve out of the box?
Evaluating Structural Generalization in Neural Machine Translation
ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic
Enhancing Automated Interpretability with Output-Centric Feature Descriptions
Identifying Semantic Divergences in Parallel Text without Annotations
Knowledge-Enhanced Evidence Retrieval for Counterargument Generation
Subspace Representations for Soft Set Operations and Sentence Similarities
Data Efficient Masked Language Modeling for Vision and Language
Story Visualization by Online Text Augmentation with Context Memory
Modelling Sentence Pairs with Tree-structured Attentive Encoder
Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization
Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking
Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling
Discourse Structures Guided Fine-grained Propaganda Identification
Sentence-level Media Bias Analysis with Event Relation Graph
EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective
Video Abnormal Event Detection by Learning to Complete Visual Cloze Tests
Evaluating the Factual Consistency of Abstractive Text Summarization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.