“本文主要以汉语委婉语作为研究对象, 基于大量人工标注, 借助机器学习有监督分类方法, 实现了较高精度的委婉语自动识别, 并基于此对1946年-2017年的《人民日报》中的委婉语历时变化发展情况进行量化统计分析。从大规模数据的角度探讨委婉语历时性发展变化、委婉语与社会之间的共变关系, 验证了语言的格雷什姆规律与更新规律。”
The heterogeneity in ML models comes from multi-sensor perceiving and multi-task learning, i. e., multi-modality multi-task (MMMT), resulting in diverse deep neural network (DNN) layers and computation patterns.
In this work, we design EF-Train, an efficient DNN training accelerator with a unified channel-level parallelism-based convolution kernel that can achieve end-to-end training on resource-limited low-power edge-level FPGAs.
To address the performance gap of English ASR models on L2 English speakers, we evaluate fine-tuning of pretrained wav2vec 2. 0 models (Baevski et al., 2020; Xu et al., 2021) on L2-ARCTIC, a non-native English speech corpus (Zhao et al., 2018) under different training settings.
On the other hand, the video dehazing algorithms, which can acquire more satisfying dehazing results by exploiting the temporal redundancy from neighborhood hazy frames, receive less attention due to the absence of the video dehazing datasets.
We find the effectiveness of existing techniques significantly affected by the absence of pre-trained models.
To address this issue, a novel meta-path-based HIN representation learning framework named mSHINE is designed to simultaneously learn multiple node representations for different meta-paths.
In this paper, we propose a Label-based Attention for Hierarchical Mutlti-label Text Classification Neural Network (LA-HCN), where the novel label-based attention module is designed to hierarchically extract important information from the text based on the labels from different hierarchy levels.
Existing multimodal emotion databases in the real-world conditions are few and small, with a limited number of subjects and expressed in a single language.
To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme.
To address this problem, we propose a dual-branch convolutional neural network to extract base features and recovered features separately.
Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) algorithms which can improve sampling efficiency by modeling and approximating system dynamics.
In addition, with a performance abstraction model to analyze the latency of neural architectures without training, our framework can quickly prune architectures that do not satisfy the specification, leading to higher efficiency.
The 55th Design Automation Conference (DAC) held its first System Design Contest (SDC) in 2018.
Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution.