arXiv subjects

Yong Cao

Publications and source records attributed to Yong Cao.

50 records · Page 3Linked to original sources

arXiv2023

Pay More Attention to Relation Exploration for Knowledge Base Question Answering

Knowledge base question answering (KBQA) is a challenging task that aims to retrieve correct answers from large-scale knowledge bases. Existing attempts primarily focus on entity representation and final answer reasoning, which results in limited supervision for this task. Moreover, the relations, which empirically determine the reasoning path selection, are not fully considered in recent advancements. In this study, we propose a novel framework, RE-KBQA, that utilizes relations in the knowledge base to enhance entity representation and introduce additional supervision. We explore guidance from relations in three aspects, including (1) distinguishing similar entities by employing a variational graph auto-encoder to learn relation importance; (2) exploring extra supervision by predicting relation distributions as soft labels with a multi-task scheme; (3) designing a relation-guided re-ranking algorithm for post-processing. Experimental results on two benchmark datasets demonstrate the effectiveness and superiority of our framework, improving the F1 score by 5.7% from 40.5 to 46.3 on CWQ and 5.8% from 62.8 to 68.5 on WebQSP, better or on par with state-of-the-art methods.

cs.CL↗

arXiv2023

Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study

The recent release of ChatGPT has garnered widespread recognition for its exceptional ability to generate human-like responses in dialogue. Given its usage by users from various nations and its training on a vast multilingual corpus that incorporates diverse cultural and societal norms, it is crucial to evaluate its effectiveness in cultural adaptation. In this paper, we investigate the underlying cultural background of ChatGPT by analyzing its responses to questions designed to quantify human cultural differences. Our findings suggest that, when prompted with American context, ChatGPT exhibits a strong alignment with American culture, but it adapts less effectively to other cultural contexts. Furthermore, by using different prompts to probe the model, we show that English prompts reduce the variance in model responses, flattening out cultural differences and biasing them towards American culture. This study provides valuable insights into the cultural implications of ChatGPT and highlights the necessity of greater diversity and cultural awareness in language technologies.

cs.CL↗

arXiv2023

Cross-Cultural Transfer Learning for Chinese Offensive Language Detection

Detecting offensive language is a challenging task. Generalizing across different cultures and languages becomes even more challenging: besides lexical, syntactic and semantic differences, pragmatic aspects such as cultural norms and sensitivities, which are particularly relevant in this context, vary greatly. In this paper, we target Chinese offensive language detection and aim to investigate the impact of transfer learning using offensive language detection data from different cultural backgrounds, specifically Korean and English. We find that culture-specific biases in what is considered offensive negatively impact the transferability of language models (LMs) and that LMs trained on diverse cultural data are sensitive to different features in Chinese offensive language detection. In a few-shot learning scenario, however, our study shows promising prospects for non-English offensive language detection with limited resources. Our findings highlight the importance of cross-cultural transfer learning in improving offensive language detection and promoting inclusive digital spaces.

cs.CL↗

arXiv2023

Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial Hemorrhage Etiology based on CT Scan

Background: To develop an artificial intelligence system that can accurately identify acute non-traumatic intracranial hemorrhage (ICH) etiology based on non-contrast CT (NCCT) scans and investigate whether clinicians can benefit from it in a diagnostic setting. Materials and Methods: The deep learning model was developed with 1868 eligible NCCT scans with non-traumatic ICH collected between January 2011 and April 2018. We tested the model on two independent datasets (TT200 and SD 98) collected after April 2018. The model's diagnostic performance was compared with clinicians's performance. We further designed a simulated study to compare the clinicians's performance with and without the deep learning system augmentation. Results: The proposed deep learning system achieved area under the receiver operating curve of 0.986 (95% CI 0.967-1.000) on aneurysms, 0.952 (0.917-0.987) on hypertensive hemorrhage, 0.950 (0.860-1.000) on arteriovenous malformation (AVM), 0.749 (0.586-0.912) on Moyamoya disease (MMD), 0.837 (0.704-0.969) on cavernous malformation (CM), and 0.839 (0.722-0.959) on other causes in TT200 dataset. Given a 90% specificity level, the sensitivities of our model were 97.1% and 90.9% for aneurysm and AVM diagnosis, respectively. The model also shows an impressive generalizability in an independent dataset SD98. The clinicians achieve significant improvements in the sensitivity, specificity, and accuracy of diagnoses of certain hemorrhage etiologies with proposed system augmentation. Conclusions: The proposed deep learning algorithms can be an effective tool for early identification of hemorrhage etiologies based on NCCT scans. It may also provide more information for clinicians for triage and further imaging examination selection.

eess.IV↗

arXiv2022

Reynolds number effects on the bistable flows over a wavy circular cylinder

The wake of wavy cylinder has been shown to exhibit bistability. Depending on the initial condition, the final state of the wake can either develop into a steady flow (state I), or periodic shedding (state II). In this paper, we perform direct numerical simulations to reveal the Reynolds number effects on these two wake states. With increasing Reynolds number, the steady vortical structures in state I wake sways back and forth in the spanwise direction, resulting in low-frequency fluctuations in drag forces, but not in lift. For state II, the increase in Reynolds number is associated with the emergence of another spectral peak in the lift coefficient. The secondary frequency is associated with highly three-dimensional vortical structures in the wake. For both states, the wakes transition to turblent flows at higher Reynolds numbers, with the development of small-scale vortices. We further study the streamwise gust flows over the wavy cylinder. The time-varying inflow velocity results in a wide range of instantaneous Reynolds number spanning from the absolutely unstable flow regime to the bistable regime. Depending on the period of the inflow velocity variation, the wake perturbations grown at the absolutely unstable flow regime can be damped out in state I wake, or grow large enough to trigger the transition state II, resulting in loss of flow control efficacy. The above analyses reveal novel flow physics of the bistable states at unexplored Reynolds numbers, and showcase the complex transition behavior between the two states in unsteady flows. The insights gained from this study improve the understanding of the wake dynamics of the wavy cylinder.

physics.flu-dyn↗

arXiv2021

Spiral Language Modeling

In almost all text generation applications, word sequences are constructed in a left-to-right (L2R) or right-to-left (R2L) manner, as natural language sentences are written either L2R or R2L. However, we find that the natural language written order is not essential for text generation. In this paper, we propose Spiral Language Modeling (SLM), a general approach that enables one to construct natural language sentences beyond the L2R and R2L order. SLM allows one to form natural language text by starting from an arbitrary token inside the result text and expanding the rest tokens around the selected ones. It makes the decoding order a new optimization objective besides the language model perplexity, which further improves the diversity and quality of the generated text. Furthermore, SLM makes it possible to manipulate the text construction process by selecting a proper starting token. SLM also introduces generation orderings as additional regularization to improve model robustness in low-resource scenarios. Experiments on 8 widely studied Neural Machine Translation (NMT) tasks show that SLM is constantly effective with up to 4.7 BLEU increase comparing to the conventional L2R decoding approach.

cs.CL↗

arXiv2020

Deep Active Learning for Remote Sensing Object Detection

Recently, CNN object detectors have achieved high accuracy on remote sensing images but require huge labor and time costs on annotation. In this paper, we propose a new uncertainty-based active learning which can select images with more information for annotation and detector can still reach high performance with a fraction of the training images. Our method not only analyzes objects' classification uncertainty to find least confident objects but also considers their regression uncertainty to declare outliers. Besides, we bring out two extra weights to overcome two difficulties in remote sensing datasets, class-imbalance and difference in images' objects amount. We experiment our active learning algorithm on DOTA dataset with CenterNet as object detector. We achieve same-level performance as full supervision with only half images. We even override full supervision with 55% images and augmented weights on least confident images.

cs.CV↗

arXiv2019

Understanding Semantics from Speech Through Pre-training

End-to-end Spoken Language Understanding (SLU) is proposed to infer the semantic meaning directly from audio features without intermediate text representation. Although the acoustic model component of an end-to-end SLU system can be pre-trained with Automatic Speech Recognition (ASR) targets, the SLU component can only learn semantic features from limited task-specific training data. In this paper, for the first time we propose to do large-scale unsupervised pre-training for the SLU component of an end-to-end SLU system, so that the SLU component may preserve semantic features from massive unlabeled audio data. As the output of the acoustic model component, i.e. phoneme posterior sequences, has much different characteristic from text sequences, we propose a novel pre-training model called BERT-PLM, which stands for Bidirectional Encoder Representations from Transformers through Permutation Language Modeling. BERT-PLM trains the SLU component on unlabeled data through a regression objective equivalent to the partial permutation language modeling objective, while leverages full bi-directional context information with BERT networks. The experiment results show that our approach out-perform the state-of-the-art end-to-end systems with over 12.5% error reduction.

eess.AS↗

arXiv2019

CreativeBioMan: Brain and Body Wearable Computing based Creative Gaming System

Current artificial intelligence (AI) technology is mainly used in rational work such as computation and logical analysis. How to make the machine as aesthetic and creative as humans has gradually gained attention. This paper presents a creative game system (i.e., CreativeBioMan) for the first time. It combines brain wave data and multimodal emotion data, and then uses an AI algorithm for intelligent decision fusion, which can be used in artistic creation, aiming at separating the artist from repeated labor creation. To imitate the process of humans' artistic creation, the creation process of the algorithm is related to artists' previous artworks and their emotion. EEG data is used to analyze the style of artists and then match them with a style from a data set of historical works. Then, universal AI algorithms are combined with the unique creativity of each artist that evolve into a personalized creation algorithm. According to the results of cloud emotion recognition, the color of the artworks is corrected so that the artist's emotions are fully reflected in the works, and thus novel works of art are created. This allows the machine to integrate the understanding of past art and emotions with the ability to create new art forms, in the same manner as humans. This paper introduces the system architecture of CreativeBioMan from two aspects: data collection of the brain and body wearable devices, as well as the intelligent decision-making fusion of models. A Testbed platform is built for an experiment and the creativity of the works produced by the system is analyzed.

cs.HC↗

arXiv2018

Learning-to-Ask: Knowledge Acquisition via 20 Questions

Almost all the knowledge empowered applications rely upon accurate knowledge, which has to be either collected manually with high cost, or extracted automatically with unignorable errors. In this paper, we study 20 Questions, an online interactive game where each question-response pair corresponds to a fact of the target entity, to acquire highly accurate knowledge effectively with nearly zero labor cost. Knowledge acquisition via 20 Questions predominantly presents two challenges to the intelligent agent playing games with human players. The first one is to seek enough information and identify the target entity with as few questions as possible, while the second one is to leverage the remaining questioning opportunities to acquire valuable knowledge effectively, both of which count on good questioning strategies. To address these challenges, we propose the Learning-to-Ask (LA) framework, within which the agent learns smart questioning strategies for information seeking and knowledge acquisition by means of deep reinforcement learning and generalized matrix factorization respectively. In addition, a Bayesian approach to represent knowledge is adopted to ensure robustness to noisy user responses. Simulating experiments on real data show that LA is able to equip the agent with effective questioning strategies, which result in high winning rates and rapid knowledge acquisition. Moreover, the questioning strategies for information seeking and knowledge acquisition boost the performance of each other, allowing the agent to start with a relatively small knowledge set and quickly improve its knowledge base in the absence of constant human supervision.

cs.AI↗

arXiv2017

An improved immersed finte element particle-in-cell method for plasma simulation

The particle-in-cell (PIC) method has been widely used for plasma simulation, because of its noise-reduction capability and moderate computational cost. The immersed finite element (IFE) method is efficient for solving interface problems on Cartesian meshes, which is desirable for PIC method. The combination of these two methods provides an effective tool for plasma simulation with complex interface/boundary. This paper introduces an improved IFE-PIC method that enhances the performance in both IFE and PIC aspects. For the electric field solver, we adopt the newly developed partially penalized IFE method with enhanced accuracy. For PIC implementation, we introduce a new interpolation technique to ensure the conservation of the charge. Numerical examples are provided to demonstrate the features of the improved IFE-PIC method.

math.NA↗

arXiv2012

Efficient and Effective Volume Visualization with Enhanced Isosurface Rendering

Compared with full volume rendering, isosurface rendering has several well recognized advantages in efficiency and accuracy. However, standard isosurface rendering has some limitations in effectiveness. First, it uses a monotone colored approach and can only visualize the geometry features of an isosurface. The lack of the capability to illustrate the material property and the internal structures behind an isosurface has been a big limitation of this method in applications. Another limitation of isosurface rendering is the difficulty to reveal physically meaningful structures, which are hidden in one or multiple isosurfaces. As such, the application requirements of extract and recombine structures of interest can not be implemented effectively with isosurface rendering. In this work, we develop an enhanced isosurface rendering technique to improve the effectiveness while maintaining the performance efficiency of the standard isosurface rendering. First, an isosurface color enhancement method is proposed to illustrate the neighborhood density and to reveal some of the internal structures. Second, we extend the structure extraction capability of isosurface rendering by enabling explicit scene exploration within a 3D-view, using surface peeling, voxel-selecting, isosurface segmentation, and multi-surface-structure visualization. Our experiments show that the color enhancement not only improves the visual fidelity of the rendering, but also reveals the internal structures without significant increase of the computational cost. Explicit scene exploration is also demonstrated as a powerful tool in some application scenarios, such as displaying multiple abdominal organs.

cs.GR↗

arXiv2009

Towards Chip-on-Chip Neuroscience: Fast Mining of Frequent Episodes Using Graphics Processors

Computational neuroscience is being revolutionized with the advent of multi-electrode arrays that provide real-time, dynamic, perspectives into brain function. Mining event streams from these chips is critical to understanding the firing patterns of neurons and to gaining insight into the underlying cellular activity. We present a GPGPU solution to mining spike trains. We focus on mining frequent episodes which captures coordinated events across time even in the presence of intervening background/"junk" events. Our algorithmic contributions are two-fold: MapConcatenate, a new computation-to-core mapping scheme, and a two-pass elimination approach to quickly find supported episodes from a large number of candidates. Together, they help realize a real-time "chip-on-chip" solution to neuroscience data mining, where one chip (the multi-electrode array) supplies the spike train data and another (the GPGPU) mines it at a scale unachievable previously. Evaluation on both synthetic and real datasets demonstrate the potential of our approach.

cs.DC↗

arXiv2009

Accelerator-Oriented Algorithm Transformation for Temporal Data Mining

Temporal data mining algorithms are becoming increasingly important in many application domains including computational neuroscience, especially the analysis of spike train data. While application scientists have been able to readily gather multi-neuronal datasets, analysis capabilities have lagged behind, due to both lack of powerful algorithms and inaccessibility to powerful hardware platforms. The advent of GPU architectures such as Nvidia's GTX 280 offers a cost-effective option to bring these capabilities to the neuroscientist's desktop. Rather than port existing algorithms onto this architecture, we advocate the need for algorithm transformation, i.e., rethinking the design of the algorithm in a way that need not necessarily mirror its serial implementation strictly. We present a novel implementation of a frequent episode discovery algorithm by revisiting "in-the-large" issues such as problem decomposition as well as "in-the-small" issues such as data layouts and memory access patterns. This is non-trivial because frequent episode discovery does not lend itself to GPU-friendly data-parallel mapping strategies. Applications to many datasets and comparisons to CPU as well as prior GPU implementations showcase the advantages of our approach.

cs.DC↗