Search Results for author:
Found 14 papers, 9 papers with code
Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations
This task requires the system to identify multiple styles of music based on its reviews on websites.
Sparse Transformer: Concentrated Attention Through Explicit Selection
Extensive experimental results on a series of natural language processing tasks, including neural machine translation, image captioning, and language modeling, all demonstrate the advantages of Sparse Transformer in model performance.
Understanding and Improving Layer Normalization
Unlike them, we find that the derivatives of the mean and variance are more important than forward normalization by re-centering and re-scaling backward gradients.
Ranked #5 on
Machine Translation
on IWSLT2015 English-Vietnamese
MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning
In this work, we explore parallel multi-scale representation learning on sequence data, striving to capture both long-range and short-range language structures.
Ranked #8 on
Machine Translation
on WMT2014 English-French
Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection
Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks.
Rethinking and Improving Natural Language Generation with Layer-Wise Multi-View Decoding
While it is common practice to draw information from only the last encoder layer, recent work has proposed to use representations from different encoder layers for diversified levels of information.
High-Likelihood Area Matters --- Rewarding Near-Correct Predictions Under Imbalanced Distributions
We find in practice that the high-likelihood area contains correct predictions for tail classes and it plays a vital role in learning imbalanced class distributions.
Learning Relation Alignment for Calibrated Cross-modal Retrieval
To bridge the semantic gap between the two modalities, previous studies mainly focus on word-region alignment at the object level, lacking the matching between the linguistic relation among the words and the visual relation among the regions.
Ranked #4 on
Image-to-Text Retrieval
on MS COCO
Topology-Imbalance Learning for Semi-Supervised Node Classification
The class imbalance problem, as an important issue in learning node representations, has drawn increasing attention from the community.
Well-classified Examples are Underestimated in Classification with Deep Neural Networks
The conventional wisdom behind learning deep classification models is to focus on bad-classified examples and ignore well-classified examples that are far from the decision boundary.
Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models
As many fine-tuned pre-trained language models~(PLMs) with promising performance are generously released, investigating better ways to reuse these models is vital as it can greatly reduce the retraining computational cost and the potential environmental side-effects.
Delving into the Openness of CLIP
However, evaluating the openness of CLIP-like models is challenging, as the models are open to arbitrary vocabulary in theory, but their accuracy varies in practice.
From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
We then design a Model Uncertainty--aware Knowledge Integration (MUKI) framework to recover the golden supervision for the student.
When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learning
Federated Learning has become a widely-used framework which allows learning a global model on decentralized local datasets under the condition of protecting local data privacy.
