arXiv subjects

Yuying Zhu

Publications and source records attributed to Yuying Zhu.

25 records · Page 2Linked to original sources

arXiv2021

MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences

Human communication is multimodal in nature; it is through multiple modalities such as language, voice, and facial expressions, that opinions and emotions are expressed. Data in this domain exhibits complex multi-relational and temporal interactions. Learning from this data is a fundamentally challenging research problem. In this paper, we propose Modal-Temporal Attention Graph (MTAG). MTAG is an interpretable graph-based neural model that provides a suitable framework for analyzing multimodal sequential data. We first introduce a procedure to convert unaligned multimodal sequence data into a graph with heterogeneous nodes and edges that captures the rich interactions across modalities and through time. Then, a novel graph fusion operation, called MTAG fusion, along with a dynamic pruning and read-out technique, is designed to efficiently process this modal-temporal graph and capture various interactions. By learning to focus only on the important interactions within the graph, MTAG achieves state-of-the-art performance on multimodal sentiment analysis and emotion recognition benchmarks, while utilizing significantly fewer model parameters.

cs.CL↗

arXiv2020

Direct visualization of ambipolar Mott transition in cuprate CuO2 planes

Identifying the essence of doped Mott insulators is one of the major outstanding problems in condensed matter physics and the key to understanding the high-temperature superconductivity in cuprates. We report real space visualization of Mott transition in Sr1-xLaxCuO2+y cuprate films that cover the entire electron- and hole-doped regimes. Tunneling conductance measurements directly on the cooper-oxide (CuO2) planes reveal a systematic shift in the Fermi level, while the fundamental Mott-Hubbard band structure remains unchanged. This is further demonstrated by exploring atomic-scale electronic response of CuO2 to substitutional dopants and intrinsic defects in a sister compound Sr0.92Nd0.08CuO2. The results could be better explained in the framework of self-modulation doping, similar to that in semiconductor heterostructures, and form a basis for developing any microscopic theories for cuprate superconductivity.

cond-mat.supr-con↗

arXiv2020

CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition

Named entity recognition (NER) in Chinese is essential but difficult because of the lack of natural delimiters. Therefore, Chinese Word Segmentation (CWS) is usually considered as the first step for Chinese NER. However, models based on word-level embeddings and lexicon features often suffer from segmentation errors and out-of-vocabulary (OOV) words. In this paper, we investigate a Convolutional Attention Network called CAN for Chinese NER, which consists of a character-based convolutional neural network (CNN) with local-attention layer and a gated recurrent unit (GRU) with global self-attention layer to capture the information from adjacent characters and sentence contexts. Also, compared to other models, not depending on any external resources like lexicons and employing small size of char embeddings make our model more practical. Extensive experimental results show that our approach outperforms state-of-the-art methods without word embedding and external lexicon resources on different domain datasets including Weibo, MSRA and Chinese Resume NER dataset.

cs.CL↗

arXiv2020

What Gives the Answer Away? Question Answering Bias Analysis on Video QA Datasets

Question answering biases in video QA datasets can mislead multimodal model to overfit to QA artifacts and jeopardize the model's ability to generalize. Understanding how strong these QA biases are and where they come from helps the community measure progress more accurately and provide researchers insights to debug their models. In this paper, we analyze QA biases in popular video question answering datasets and discover pretrained language models can answer 37-48% questions correctly without using any multimodal context information, far exceeding the 20% random guess baseline for 5-choose-1 multiple-choice questions. Our ablation study shows biases can come from annotators and type of questions. Specifically, annotators that have been seen during training are better predicted by the model and reasoning, abstract questions incur more biases than factual, direct questions. We also show empirically that using annotator-non-overlapping train-test splits can reduce QA biases for video QA datasets.

cs.CL↗

arXiv2019

Decoding and mapping task states of the human brain via deep learning

Support vector machine (SVM) based multivariate pattern analysis (MVPA) has delivered promising performance in decoding specific task states based on functional magnetic resonance imaging (fMRI) of the human brain. Conventionally, the SVM-MVPA requires careful feature selection/extraction according to expert knowledge. In this study, we propose a deep neural network (DNN) for directly decoding multiple brain task states from fMRI signals of the brain without any burden for feature handcrafts. We trained and tested the DNN classifier using task fMRI data from the Human Connectome Project's S1200 dataset (N=1034). In tests to verify its performance, the proposed classification method identified seven tasks with an average accuracy of 93.7%. We also showed the general applicability of the DNN for transfer learning to small datasets (N=43), a situation encountered in typical neuroscience research. The proposed method achieved an average accuracy of 89.0% and 94.7% on a working memory task and a motor classification task, respectively, higher than the accuracy of 69.2% and 68.6% obtained by the SVM-MVPA. A network visualization analysis showed that the DNN automatically detected features from areas of the brain related to each task. Without incurring the burden of handcrafting the features, the proposed deep decoding method can classify brain task states highly accurately, and is a powerful tool for fMRI researchers.

q-bio.NC↗

arXiv2019

Superconductivity above 28 K in single unit cell FeSe films interfaced with GaO$_{2-δ}$ layer on NdGaO$_{3}$(110)

We prepared single unit cell FeSe films on GaO$_{2-δ}$ terminated perovskite NdGaO$_{3}$(110) substrates and performed ex situ transport and scanning transmission electron microscopy measurements on the FeTe protected films. Our experimental measurements showed that the single unit cell FeSe films interfaced with GaO$_{2-δ}$ layer are electron doped via interface charge transfer. Most importantly, this type of heterostructure can host interface enhanced superconductivity with an onset temperature of about 28 K, which is much higher than the value of 8 K in bulk FeSe. Our work indicates that FeSe/GaO$_{2-δ}$can be a comparative platform with the FeSe/TiO$_{2-δ}$ family for understanding the mechanism of interface enhanced high temperature superconductivity.

cond-mat.supr-con↗

arXiv2018

Electric-Field Induced Superconductor-Insulator Transitions in Exfoliated Bi$_2$Sr$_2$CaCu$_2$O$_{8+δ}$ Flakes

We realize superconductor-insulator transitions (SIT) in mechanically exfoliated Bi$_2$Sr$_2$CaCu$_2$O$_{8+δ}$ (BSCCO) flakes and address simultaneously their transport properties as well as the evolution of density of states. Back-gating via the solid ion conductor engenders a reversible SIT in BSCCO, as lithium ions from the substrate are electrically driven into and out of BSCCO. Scaling analysis indicates that the SIT follows the theoretical description of a two-dimensional quantum phase transition (2D-QPT). We further carry out tunneling spectroscopy in graphite(G)/BSCCO heterojunctions. We observe V-shaped gaps in the critical regime of the SIT. The density of states in BSCCO gets symmetrically suppressed by further going into the insulating regime. Our technique of combining solid state gating with tunneling spectroscopy can be easily applied to the study of other two-dimensional materials.

cond-mat.supr-con↗