Paper Reading AI Learner

Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity

2021-11-16 11:12:30
Sheshera Mysore, Arman Cohan, Tom Hope

Abstract

We present Aspire, a new scientific document similarity model based on matching fine-grained aspects. Our model is trained using co-citation contexts that describe related paper aspects as a novel form of textual supervision. We use multi-vector document representations, recently explored in settings with short query texts but under-explored in the challenging document-document setting. We present a fast method that involves matching only single sentence pairs, and a method that makes sparse multiple matches with optimal transport. Our model improves performance on document similarity tasks across four datasets. Moreover, our fast single-match method achieves competitive results, opening up the possibility of applying fine-grained document similarity models to large-scale scientific corpora.

Abstract (translated)

URL

https://arxiv.org/abs/2111.08366

PDF

https://arxiv.org/pdf/2111.08366.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot