Search arXiv⌕ Search

arXiv subjects

Yue Zhang

Publications and source records attributed to Yue Zhang.

At least 505 records · Page 28Linked to original sources
arXiv2023

Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information

Argument structure extraction (ASE) aims to identify the discourse structure of arguments within documents. Previous research has demonstrated that contextual information is crucial for developing an effective ASE model. However, we observe that merely concatenating sentences in a contextual window does not fully utilize contextual information and can sometimes lead to excessive attention on less informative sentences. To tackle this challenge, we propose an Efficient Context-aware ASE model (ECASE) that fully exploits contextual information by enhancing modeling capacity and augmenting training data. Specifically, we introduce a sequence-attention module and distance-weighted similarity loss to aggregate contextual information and argumentative information. Additionally, we augment the training data by randomly masking discourse markers and sentences, which reduces the model's reliance on specific words or less informative sentences. Our experiments on five datasets from various domains demonstrate that our model achieves state-of-the-art performance. Furthermore, ablation studies confirm the effectiveness of each module in our model.

cs.CL↗
arXiv2023

Lung Nodule Segmentation and Uncertain Region Prediction with an Uncertainty-Aware Attention Mechanism

Radiologists possess diverse training and clinical experiences, leading to variations in the segmentation annotations of lung nodules and resulting in segmentation uncertainty.Conventional methods typically select a single annotation as the learning target or attempt to learn a latent space comprising multiple annotations. However, these approaches fail to leverage the valuable information inherent in the consensus and disagreements among the multiple annotations. In this paper, we propose an Uncertainty-Aware Attention Mechanism (UAAM) that utilizes consensus and disagreements among multiple annotations to facilitate better segmentation. To this end, we introduce the Multi-Confidence Mask (MCM), which combines a Low-Confidence (LC) Mask and a High-Confidence (HC) Mask.The LC mask indicates regions with low segmentation confidence, where radiologists may have different segmentation choices. Following UAAM, we further design an Uncertainty-Guide Multi-Confidence Segmentation Network (UGMCS-Net), which contains three modules: a Feature Extracting Module that captures a general feature of a lung nodule, an Uncertainty-Aware Module that produces three features for the the annotations' union, intersection, and annotation set, and an Intersection-Union Constraining Module that uses distances between the three features to balance the predictions of final segmentation and MCM. To comprehensively demonstrate the performance of our method, we propose a Complex Nodule Validation on LIDC-IDRI, which tests UGMCS-Net's segmentation performance on lung nodules that are difficult to segment using common methods. Experimental results demonstrate that our method can significantly improve the segmentation performance on nodules that are difficult to segment using conventional methods.

eess.IV↗
arXiv2023

Radiation hardness study of BC408 plastic scintillator under 80 MeV proton beam irradiations

To investigate the 1.6 GeV high-energy proton beam detector utilized in the CSNS Phase-II upgrade project, a plastic scintillator detector presents a viable option due to its superior radiation hardness. This study investigates the effects of irradiation damage on a BC408 plastic scintillator induced by 80 MeV protons, including absorption and fluorescence spectroscopy, and light yield tests of BC408 pre- and post-proton irradiation, with a focus on determining the radiation resistance threshold of BC408. The results indicate that the performance of BC408 remains unimpaired at absorbed doses up to 5.14*10^3 Gy/cm3, demonstrating its ability to absorb 1.63*10^13 p/cm3 1.6 GeV protons while maintaining stability. This suggests that BC408 could potentially be used as the 1.6 GeV high-energy proton beam detector in the CSNS Phase-II upgrade project.

physics.ins-det↗
arXiv2023

Interactive Design and Optics-Based Visualization of Arbitrary Non-Euclidean Kaleidoscopic Orbifolds

Orbifolds are a modern mathematical concept that arises in the research of hyperbolic geometry with applications in computer graphics and visualization. In this paper, we make use of rooms with mirrors as the visual metaphor for orbifolds. Given any arbitrary two-dimensional kaleidoscopic orbifold, we provide an algorithm to construct a Euclidean, spherical, or hyperbolic polygon to match the orbifold. This polygon is then used to create a room for which the polygon serves as the floor and the ceiling. With our system that implements Möbius transformations, the user can interactively edit the scene and see the reflections of the edited objects. To correctly visualize non-Euclidean orbifolds, we adapt the rendering algorithms to account for the geodesics in these spaces, which light rays follow. Our interactive orbifold design system allows the user to create arbitrary two-dimensional kaleidoscopic orbifolds. In addition, our mirror-based orbifold visualization approach has the potential of helping our users gain insight on the orbifold, including its orbifold notation as well as its universal cover, which can also be the spherical space and the hyperbolic space.

cs.GR↗
arXiv2023

Global Topology of 3D Symmetric Tensor Fields

There have been recent advances in the analysis and visualization of 3D symmetric tensor fields, with a focus on the robust extraction of tensor field topology. However, topological features such as degenerate curves and neutral surfaces do not live in isolation. Instead, they intriguingly interact with each other. In this paper, we introduce the notion of {\em topological graph} for 3D symmetric tensor fields to facilitate global topological analysis of such fields. The nodes of the graph include degenerate curves and regions bounded by neutral surfaces in the domain. The edges in the graph denote the adjacency information between the regions and degenerate curves. In addition, we observe that a degenerate curve can be a loop and even a knot and that two degenerate curves (whether in the same region or not) can form a link. We provide a definition and theoretical analysis of individual degenerate curves in order to help understand why knots and links may occur. Moreover, we differentiate between wedges and trisectors, thus making the analysis more detailed about degenerate curves. We incorporate this information into the topological graph. Such a graph can not only reveal the global structure in a 3D symmetric tensor field but also allow two symmetric tensor fields to be compared. We demonstrate our approach by applying it to solid mechanics and material science data sets.

cs.GR↗
arXiv2023

On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective

ChatGPT is a recent chatbot service released by OpenAI and is receiving increasing attention over the past few months. While evaluations of various aspects of ChatGPT have been done, its robustness, i.e., the performance to unexpected inputs, is still unclear to the public. Robustness is of particular concern in responsible AI, especially for safety-critical applications. In this paper, we conduct a thorough evaluation of the robustness of ChatGPT from the adversarial and out-of-distribution (OOD) perspective. To do so, we employ the AdvGLUE and ANLI benchmarks to assess adversarial robustness and the Flipkart review and DDXPlus medical diagnosis datasets for OOD evaluation. We select several popular foundation models as baselines. Results show that ChatGPT shows consistent advantages on most adversarial and OOD classification and translation tasks. However, the absolute performance is far from perfection, which suggests that adversarial and OOD robustness remains a significant threat to foundation models. Moreover, ChatGPT shows astounding performance in understanding dialogue-related texts and we find that it tends to provide informal suggestions for medical tasks instead of definitive answers. Finally, we present in-depth discussions of possible research directions.

cs.AI↗
arXiv2023

Scalable Hypergraph Visualization

Hypergraph visualization has many applications in network data analysis. Recently, a polygon-based representation for hypergraphs has been proposed with demonstrated benefits. However, the polygon-based layout often suffers from excessive self-intersections when the input dataset is relatively large. In this paper, we propose a framework in which the hypergraph is iteratively simplified through a set of atomic operations. Then, the layout of the simplest hypergraph is optimized and used as the foundation for a reverse process that brings the simplest hypergraph back to the original one, but with an improved layout. At the core of our approach is the set of atomic simplification operations and an operation priority measure to guide the simplification process. In addition, we introduce necessary definitions and conditions for hypergraph planarity within the polygon representation. We extend our approach to handle simultaneous simplification and layout optimization for both the hypergraph and its dual. We demonstrate the utility of our approach with datasets from a number of real-world applications.

cs.GR↗
arXiv2023

POAR: Towards Open Vocabulary Pedestrian Attribute Recognition

Pedestrian attribute recognition (PAR) aims to predict the attributes of a target pedestrian in a surveillance system. Existing methods address the PAR problem by training a multi-label classifier with predefined attribute classes. However, it is impossible to exhaust all pedestrian attributes in the real world. To tackle this problem, we develop a novel pedestrian open-attribute recognition (POAR) framework. Our key idea is to formulate the POAR problem as an image-text search problem. We design a Transformer-based image encoder with a masking strategy. A set of attribute tokens are introduced to focus on specific pedestrian parts (e.g., head, upper body, lower body, feet, etc.) and encode corresponding attributes into visual embeddings. Each attribute category is described as a natural language sentence and encoded by the text encoder. Then, we compute the similarity between the visual and text embeddings of attributes to find the best attribute descriptions for the input images. Different from existing methods that learn a specific classifier for each attribute category, we model the pedestrian at a part-level and explore the searching method to handle the unseen attributes. Finally, a many-to-many contrastive (MTMC) loss with masked tokens is proposed to train the network since a pedestrian image can comprise multiple attributes. Extensive experiments have been conducted on benchmark PAR datasets with an open-attribute setting. The results verified the effectiveness of the proposed POAR method, which can form a strong baseline for the POAR task. Our code is available at \url{https://github.com/IvyYZ/POAR}.

cs.CV↗
arXiv2023

DPMix: Mixture of Depth and Point Cloud Video Experts for 4D Action Segmentation

In this technical report, we present our findings from the research conducted on the Human-Object Interaction 4D (HOI4D) dataset for egocentric action segmentation task. As a relatively novel research area, point cloud video methods might not be good at temporal modeling, especially for long point cloud videos (\eg, 150 frames). In contrast, traditional video understanding methods have been well developed. Their effectiveness on temporal modeling has been widely verified on many large scale video datasets. Therefore, we convert point cloud videos into depth videos and employ traditional video modeling methods to improve 4D action segmentation. By ensembling depth and point cloud video methods, the accuracy is significantly improved. The proposed method, named Mixture of Depth and Point cloud video experts (DPMix), achieved the first place in the 4D Action Segmentation Track of the HOI4D Challenge 2023.

cs.CV↗
arXiv2023

Multi-representations Space Separation based Graph-level Anomaly-aware Detection

Graph structure patterns are widely used to model different area data recently. How to detect anomalous graph information on these graph data has become a popular research problem. The objective of this research is centered on the particular issue that how to detect abnormal graphs within a graph set. The previous works have observed that abnormal graphs mainly show node-level and graph-level anomalies, but these methods equally treat two anomaly forms above in the evaluation of abnormal graphs, which is contrary to the fact that different types of abnormal graph data have different degrees in terms of node-level and graph-level anomalies. Furthermore, abnormal graphs that have subtle differences from normal graphs are easily escaped detection by the existing methods. Thus, we propose a multi-representations space separation based graph-level anomaly-aware detection framework in this paper. To consider the different importance of node-level and graph-level anomalies, we design an anomaly-aware module to learn the specific weight between them in the abnormal graph evaluation process. In addition, we learn strictly separate normal and abnormal graph representation spaces by four types of weighted graph representations against each other including anchor normal graphs, anchor abnormal graphs, training normal graphs, and training abnormal graphs. Based on the distance error between the graph representations of the test graph and both normal and abnormal graph representation spaces, we can accurately determine whether the test graph is anomalous. Our approach has been extensively evaluated against baseline methods using ten public graph datasets, and the results demonstrate its effectiveness.

cs.LG↗
arXiv2023

Improving Text Matching in E-Commerce Search with A Rationalizable, Intervenable and Fast Entity-Based Relevance Model

Discovering the intended items of user queries from a massive repository of items is one of the main goals of an e-commerce search system. Relevance prediction is essential to the search system since it helps improve performance. When online serving a relevance model, the model is required to perform fast and accurate inference. Currently, the widely used models such as Bi-encoder and Cross-encoder have their limitations in accuracy or inference speed respectively. In this work, we propose a novel model called the Entity-Based Relevance Model (EBRM). We identify the entities contained in an item and decompose the QI (query-item) relevance problem into multiple QE (query-entity) relevance problems; we then aggregate their results to form the QI prediction using a soft logic formulation. The decomposition allows us to use a Cross-encoder QE relevance module for high accuracy as well as cache QE predictions for fast online inference. Utilizing soft logic makes the prediction procedure interpretable and intervenable. We also show that pretraining the QE module with auto-generated QE data from user logs can further improve the overall performance. The proposed method is evaluated on labeled data from e-commerce websites. Empirical results show that it achieves promising improvements with computation efficiency.

cs.IR↗
arXiv2023

ConTrack: Contextual Transformer for Device Tracking in X-ray

Device tracking is an important prerequisite for guidance during endovascular procedures. Especially during cardiac interventions, detection and tracking of guiding the catheter tip in 2D fluoroscopic images is important for applications such as mapping vessels from angiography (high dose with contrast) to fluoroscopy (low dose without contrast). Tracking the catheter tip poses different challenges: the tip can be occluded by contrast during angiography or interventional devices; and it is always in continuous movement due to the cardiac and respiratory motions. To overcome these challenges, we propose ConTrack, a transformer-based network that uses both spatial and temporal contextual information for accurate device detection and tracking in both X-ray fluoroscopy and angiography. The spatial information comes from the template frames and the segmentation module: the template frames define the surroundings of the device, whereas the segmentation module detects the entire device to bring more context for the tip prediction. Using multiple templates makes the model more robust to the change in appearance of the device when it is occluded by the contrast agent. The flow information computed on the segmented catheter mask between the current and the previous frame helps in further refining the prediction by compensating for the respiratory and cardiac motions. The experiments show that our method achieves 45% or higher accuracy in detection and tracking when compared to state-of-the-art tracking models.

cs.CV↗
arXiv2023

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation

Most existing cross-lingual summarization (CLS) work constructs CLS corpora by simply and directly translating pre-annotated summaries from one language to another, which can contain errors from both summarization and translation processes. To address this issue, we propose ConvSumX, a cross-lingual conversation summarization benchmark, through a new annotation schema that explicitly considers source input context. ConvSumX consists of 2 sub-tasks under different real-world scenarios, with each covering 3 language directions. We conduct thorough analysis on ConvSumX and 3 widely-used manually annotated CLS corpora and empirically find that ConvSumX is more faithful towards input text. Additionally, based on the same intuition, we propose a 2-Step method, which takes both conversation and summary as input to simulate human annotation process. Experimental results show that 2-Step method surpasses strong baselines on ConvSumX under both automatic and human evaluation. Analysis shows that both source input text and summary are crucial for modeling cross-lingual summaries.

cs.CL↗
arXiv2023

Partial Linear Cox Model with Deep ReLU Networks for Interval-Censored Failure Time Data

The partial linear Cox model for interval-censoring is well-studied under the additive assumption but is still under-investigated without this assumption. In this paper, we propose to use a deep ReLU neural network to estimate the nonparametric components of a partial linear Cox model for interval-censored data. This model not only retains the nice interpretability of the parametric component but also improves the predictive power compared to the partial linear additive Cox model. We derive the convergence rate of the proposed estimator and show that it can break the curse of dimensionality under some certain smoothness assumptions. Based on such rate, the asymptotic normality and the semiparametric efficiency are also established. Intensive simulation studies are carried out to demonstrate the finite sample performance on both estimation and prediction. The proposed estimation procedure is illustrated on a real dataset.

stat.ME↗
arXiv2023

Spin Swapping for an Exchange Magnon Spin Current

We propose the spin swapping effect for an exchange magnon spin current in a perpendicularly magnetized ferromagnetic medium with in plane anisotropy on the surface. The excitation of a magnon current flowing along an in-plane direction with an out-of-plane spin polarization leads to the generation of a secondary exchange spin current propagating along the out-of-plane direction, characterized by an in-plane spin polarization. The resulting exchange magnon spin current can induce an inverse spin Hall voltage of micro-volts. The exchange coupling at the interface between regions with different magnetic anisotropies plays a crucial role in generating the spin swapping effect. This is in contrast to the recently reported spin swapping for an exchange spin current in a canted antiferromagnet due to the Dzyaloshiskii-Moriya interaction.

cond-mat.mes-hall↗
arXiv2023

Explicit Syntactic Guidance for Neural Text Generation

Most existing text generation models follow the sequence-to-sequence paradigm. Generative Grammar suggests that humans generate natural language texts by learning language grammar. We propose a syntax-guided generation schema, which generates the sequence guided by a constituency parse tree in a top-down direction. The decoding process can be decomposed into two parts: (1) predicting the infilling texts for each constituent in the lexicalized syntax context given the source sentence; (2) mapping and expanding each constituent to construct the next-level syntax context. Accordingly, we propose a structural beam search method to find possible syntax structures hierarchically. Experiments on paraphrase generation and machine translation show that the proposed method outperforms autoregressive baselines, while also demonstrating effectiveness in terms of interpretability, controllability, and diversity.

cs.CL↗
arXiv2023

Token-Level Fitting Issues of Seq2seq Models

Sequence-to-sequence (seq2seq) models have been widely used for natural language processing, computer vision, and other deep learning tasks. We find that seq2seq models trained with early-stopping suffer from issues at the token level. In particular, while some tokens in the vocabulary demonstrate overfitting, others underfit when training is stopped. Experiments show that the phenomena are pervasive in different models, even in fine-tuned large pretrained-models. We identify three major factors that influence token-level fitting, which include token frequency, parts-of-speech, and prediction discrepancy. Further, we find that external factors such as language, model size, domain, data scale, and pretraining can also influence the fitting of tokens.

cs.CL↗
arXiv2023

Distributed Marker Representation for Ambiguous Discourse Markers and Entangled Relations

Discourse analysis is an important task because it models intrinsic semantic structures between sentences in a document. Discourse markers are natural representations of discourse in our daily language. One challenge is that the markers as well as pre-defined and human-labeled discourse relations can be ambiguous when describing the semantics between sentences. We believe that a better approach is to use a contextual-dependent distribution over the markers to express discourse information. In this work, we propose to learn a Distributed Marker Representation (DMR) by utilizing the (potentially) unlimited discourse marker data with a latent discourse sense, thereby bridging markers with sentence pairs. Such representations can be learned automatically from data without supervision, and in turn provide insights into the data itself. Experiments show the SOTA performance of our DMR on the implicit discourse relation recognition task and strong interpretability. Our method also offers a valuable tool to understand complex ambiguity and entanglement among discourse markers and manually defined discourse relations.

cs.CL↗