抽象语义表示到文本(AMR-to-Text)生成的任务是给定AMR图, 生成相同语义表示的文本。可以把此任务当作一个从源端AMR图到目标端句子的机器翻译任务。目前存在的一些方法都在探索如何更好的对图结构进行建模。然而, 它们都存在一个未限定的问题, 因为在生成阶段许多句法的决策并不受语义图的约束, 从而忽略了句子内部潜藏的句法信息。为了明确考虑这一不足, 该文提出一种直接而有效的方法, 显示的在AMR-to-Text生成的任务中融入句法信息, 并在Transformer和目前该任务最优性能的模型上进行了实验。实验结果表明, 在现存的两份标准英文数据集LDC2018E86和LDC2017T10上, 都取得了显著的提升, 达到了新的最高性能。
The deep learning-based speech enhancement (SE) methods always take the clean speech's waveform or time-frequency spectrum feature as the learning target, and train the deep neural network (DNN) by reducing the error loss between the DNN's output and the target.
In speech enhancement (SE), phase estimation is important for perceptual quality, so many methods take clean speech's complex short-time Fourier transform (STFT) spectrum or the complex ideal ratio mask (cIRM) as the learning target.
This paper focuses on the research of micro-expression recognition (MER) and proposes a flexible and reliable deep learning method called learning to rank onset-occurring-offset representations (LTR3O).
Despite significant progress in video question answering (VideoQA), existing methods fall short of questions that require causal/temporal reasoning across frames.
Ranked #10 on Video Question Answering on NExT-QA
The study is mainly motivated by that random views, used in contrastive learning, and random masked (visible) patches, used in masked image modeling, are often about object parts.
By simulating the attack mechanism as the safety test, SafeCompress can automatically compress a big model to a small one following the dynamic sparse training paradigm.
In the last few years, automated recommendation systems have been a major focus in the music field, where companies such as Spotify, Amazon, and Apple are competing in the ability to generate the most personalized music suggestions for their users.
In the second stage, we propose a simple and effective method for evaluating the confidence of pseudo-labels based on classification discrimination, and by learning consistency from high-quality pseudo-labels, we further refine the localization network to get better localization performance.
In this paper, we proposed Sky Computing, a load-balanced model parallelism framework to adaptively allocate the weights to devices.
This paper presents a comprehensive review of the existing ramp merging strategies leveraging CAVs, focusing on the latest trends and developments in the research field.
The strategy is formulated under an optimization framework, where the optimal control plan is determined based on real-time traffic conditions.
In this paper, we notice that the class weights of categories that tend to share many adjacent boundary pixels lack discrimination, thereby limiting the performance.
Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map.
It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable matching for MVS.
As a result, deep learning models developed for sequence modeling, like recurrent neural networks (RNNs) are common architecture for EHR-based clinical events predictive models.
We propose a general formulation for continuous treatment recommendation problems in settings with clinical survival data, which we call the Deep Survival Dose Response Function (DeepSDRF).
Freeway on-ramps are typical bottlenecks in the freeway network due to the frequent disturbances caused by their associated merging, weaving, and lane-changing behaviors.
Due to boundary ambiguity and over-segmentation issues, identifying all the frames in long untrimmed videos is still challenging.
Ranked #12 on Action Segmentation on GTEA
Non-locality sharing amongmultiple observers is predicted and experimentally observed.
We present a new math-physics modeling approach, called canonical quantization with numerical mode-decomposition, for capturing the physics of how incoming photons interact with finite-sized dispersive media, which is not describable by the previous Fano-diagonalization methods.
Quantization Quantum Physics
Causal inference in longitudinal observational health data often requires the accurate estimation of treatment effects on time-to-event outcomes in the presence of time-varying covariates.
With the ever-growing complexity of primary health care system, proactive patient failure management is an effective way to enhancing the availability of health care resource.
Deep neural networks have achieved great success in computer vision, thanks to their ability in extracting category-relevant semantic features.
In quantum mechanics, a norm squared wave function can be interpreted as the probability density that describes the likelihood of a particle to be measured in a given position or momentum.
The aim of clinical effectiveness research using repositories of electronic health records is to identify what health interventions 'work best' in real-world settings.
Recent studies on AMR-to-text generation often formalize the task as a sequence-to-sequence (seq2seq) learning problem by converting an Abstract Meaning Representation (AMR) graph into a word sequence.
4 code implementations • 14 May 2019 • Weitian Li, Haiguang Xu, Zhixian Ma, Dan Hu, Zhenghao Zhu, Chenxi Shan, Jingying Wang, Junhua Gu, Dongchao Zheng, Xiaoli Lian, Qian Zheng, Yu Wang, Jie Zhu, Xiang-Ping Wu
The overwhelming foreground contamination is one of the primary impediments to probing the EoR through measuring the redshifted 21 cm signal.
Cosmology and Nongalactic Astrophysics
When applying the foreground removal methods to uncover the faint cosmological signal from the epoch of reionization (EoR), the foreground spectra are assumed to be smooth.
In this paper, we propose a general framework for image classification using the attention mechanism and global context, which could incorporate with various network architectures to improve their performance.
In this work, we propose a morphology generation framework for two typical radio galaxies namely Fanaroff-Riley type-I (FRI) and type-II (FRII) with deep neural network based autoencoder (DNNAE) and Gaussian mixture models (GMMs).
Building on top of the powerful concept of semantic learning, this paper proposes a Recurrent Binary Embedding (RBE) model that learns compact representations for real-time retrieval.
Built on top of a representative DNN model called Deep Crossing, and two forest/tree-based models including XGBoost and LightGBM, a two-step Deep Embedding Forest algorithm is demonstrated to achieve on-par or slightly better performance as compared with the DNN counterpart, with only a fraction of serving time on conventional hardware.
An approach to recognize the point sources (PS) in the X-ray astronomical images using our newly designed granular binary-tree support vector machine (GBT-SVM) classifier is proposed.