Search Results for author:
Found 10 papers, 3 papers with code
Can Large Language Models Recall Reference Location Like Humans?
When completing knowledge-intensive tasks, humans sometimes need not just an answer but also a corresponding reference passage for auxiliary reading.
A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling
Motivated by this, we propose a positive-augmentation and positive-mixup positive-unlabeled metric learning framework (P3M).
Document-level RE with incomplete labeling
Metric Learning
+1
PEGA: Personality-Guided Preference Aggregator for Ephemeral Group Recommendation
The role of personality in our approach is twofold: (1) To estimate individual users' importance in a group and provide explainability; (2) to alleviate the data sparsity issue that occurred in ephemeral groups.
Self-Attentive Sequential Recommendation with Cheap Causal Convolutions
We evaluate the effectiveness of the proposed model in terms of both accurate and calibrated sequential recommendation.
A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling
To solve the common incomplete labeling problem, we propose a unified positive-unlabeled learning framework - shift and squared ranking loss positive-unlabeled (SSR-PU) learning.
DACSR: Decoupled-Aggregated End-to-End Calibrated Sequential Recommendation
In this work, we focus on the calibrated recommendations for sequential recommendation, which is connected to both fairness and diversity.
Pyramid Focusing Network for mutation prediction and classification in CT images
Predicting the mutation status of genes in tumors is of great clinical significance.
Cascaded Detail-Preserving Networks for Super-Resolution of Document Images
The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results.
Automatically Generating Macro Research Reports from a Piece of News
As we all know, it requires the macro analysts to write such reports within a short period of time after the important economic news are released.
Adaptive Scenario Discovery for Crowd Counting
Crowd counting, i. e., estimation number of the pedestrian in crowd images, is emerging as an important research problem with the public security applications.
