arXiv subjects

Chao Zhao

Publications and source records attributed to Chao Zhao.

51 records · Page 3Linked to original sources

arXiv2022

Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoning

Document-level Relation Extraction (DRE) aims to recognize the relations between two entities. The entity may correspond to multiple mentions that span beyond sentence boundary. Few previous studies have investigated the mention integration, which may be problematic because coreferential mentions do not equally contribute to a specific relation. Moreover, prior efforts mainly focus on reasoning at entity-level rather than capturing the global interactions between entity pairs. In this paper, we propose two novel techniques, Context Guided Mention Integration and Inter-pair Reasoning (CGM2IR), to improve the DRE. Instead of simply applying average pooling, the contexts are utilized to guide the integration of coreferential mentions in a weighted sum manner. Additionally, inter-pair reasoning executes an iterative algorithm on the entity pair graph, so as to model the interdependency of relations. We evaluate our CGM2IR model on three widely used benchmark datasets, namely DocRED, CDR, and GDA. Experimental results show that our model outperforms previous state-of-the-art models.

cs.CL↗

arXiv2021

"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding

When reading a literary piece, readers often make inferences about various characters' roles, personalities, relationships, intents, actions, etc. While humans can readily draw upon their past experiences to build such a character-centric view of the narrative, understanding characters in narratives can be a challenging task for machines. To encourage research in this field of character-centric narrative understanding, we present LiSCU -- a new dataset of literary pieces and their summaries paired with descriptions of characters that appear in them. We also introduce two new tasks on LiSCU: Character Identification and Character Description Generation. Our experiments with several pre-trained language models adapted for these tasks demonstrate that there is a need for better models of narrative comprehension.

cs.CL↗

arXiv2021

Realization of quasicrystalline quadrupole topological insulators in electrical circuits

Quadrupole topological insulators are a new class of topological insulators with quantized quadrupole moments, which support protected gapless corner states. The experimental demonstrations of quadrupole-topological insulators were reported in a series of artificial materials, such as photonic crystals, acoustic crystals, and electrical circuits. In all these cases, the underlying structures have discrete translational symmetry and thus are periodic. Here we experimentally realize two-dimensional aperiodic-quasicrystalline quadrupole-topological insulators by constructing them in electrical circuits, and observe the spectrally and spatially localized corner modes. In measurement, the modes appear as topological boundary resonances in the corner impedance spectra. Additionally, we demonstrate the robustness of corner modes on the circuit. Our circuit design may be extended to study topological phases in higher-dimensional aperiodic structures.

cond-mat.mes-hall↗

arXiv2020

All-Linear Multistate Magnetic Switching Induced by Electrical Current

We present an alternative mechanism to control the domain wall motion, whose directions are manipulated by the amplitude of electrical currents when modulating the ratio of D/A (constants of Dzyaloshinskii-Moriya interaction over exchange interaction). To confirm this mechanism, we observe this type of domain wall motion and demonstrate linear magnetic switching without hysteresis effect via adjusting the D/A of Ta/Pt/Co/Ta multilayer device with ion implantations. We further find field-free biased and chirally controllable multistate switching at the lateral interface of ion exposed and unexposed area, which is due to the current induced Neel wall motion and a strong exchange coupling at this interface.

physics.app-ph↗

arXiv2019

Weakly-Supervised Opinion Summarization by Leveraging External Information

Opinion summarization from online product reviews is a challenging task, which involves identifying opinions related to various aspects of the product being reviewed. While previous works require additional human effort to identify relevant aspects, we instead apply domain knowledge from external sources to automatically achieve the same goal. This work proposes AspMem, a generative method that contains an array of memory cells to store aspect-related knowledge. This explicit memory can help obtain a better opinion representation and infer the aspect information more precisely. We evaluate this method on both aspect identification and opinion summarization tasks. Our experiments show that AspMem outperforms the state-of-the-art methods even though, unlike the baselines, it does not rely on human supervision which is carefully handcrafted for the given tasks.

cs.CL↗

arXiv2019

Deep Dexterous Grasping of Novel Objects from a Single View

Dexterous grasping of a novel object given a single view is an open problem. This paper makes several contributions to its solution. First, we present a simulator for generating and testing dexterous grasps. Second we present a data set, generated by this simulator, of 2.4 million simulated dexterous grasps of variations of 294 base objects drawn from 20 categories. Third, we present a basic architecture for generation and evaluation of dexterous grasps that may be trained in a supervised manner. Fourth, we present three different evaluative architectures, employing ResNet-50 or VGG16 as their visual backbone. Fifth, we train, and evaluate seventeen variants of generative-evaluative architectures on this simulated data set, showing improvement from 69.53% grasp success rate to 90.49%. Finally, we present a real robot implementation and evaluate the four most promising variants, executing 196 real robot grasps in total. We show that our best architectural variant achieves a grasp success rate of 87.8% on real novel objects seen from a single view, improving on a baseline of 57.1%.

cs.RO↗

arXiv2019

Neural Entropic Estimation: A faster path to mutual information estimation

We point out a limitation of the mutual information neural estimation (MINE) where the network fails to learn at the initial training phase, leading to slow convergence in the number of training iterations. To solve this problem, we propose a faster method called the mutual information neural entropic estimation (MI-NEE). Our solution first generalizes MINE to estimate the entropy using a custom reference distribution. The entropy estimate can then be used to estimate the mutual information. We argue that the seemingly redundant intermediate step of entropy estimation allows one to improve the convergence by an appropriate reference distribution. In particular, we show that MI-NEE reduces to MINE in the special case when the reference distribution is the product of marginal distributions, but faster convergence is possible by choosing the uniform distribution as the reference distribution instead. Compared to the product of marginals, the uniform distribution introduces more samples in low-density regions and fewer samples in high-density regions, which appear to lead to an overall larger gradient for faster convergence.

cs.IT↗

arXiv2018

Heterogeneous Memristive Devices Enabled by Magnetic Tunnel Junction Nanopillars Surrounded by Resistive Silicon Switches

Emerging non-volatile memories (NVMs) have currently attracted great interest for their potential applications in advanced low-power information storage and processing technologies. Conventional NVMs, such as magnetic random access memory (MRAM) and resistive random access memory (RRAM) suffer from limitations of low tunnel magnetoresistance (TMR), low access speed or finite endurance. NVMs with synergetic advantages are still highly desired for future computer architectures. Here, we report a heterogeneous memristive device composed of a magnetic tunnel junction (MTJ) nanopillar surrounded by resistive silicon switches, named resistively enhanced MTJ (Re-MTJ), that may be utilized for novel memristive memories, enabling new functionalities that are inaccessible for conventional NVMs. The Re-MTJ device features a high ON/OFF ratio of >1000% and multilevel resistance behaviour by combining magnetic switching together with resistive switching mechanisms. The magnetic switching originates from the MTJ, while the resistive switching is induced by a point-switching filament process that is related to the mobile oxygen ions. Microscopic evidence of silicon aggregated as nanocrystals along the edges of the nanopillars verifies the synergetic mechanism of the heterogeneous memristive device. This device may provide new possibilities for advanced memristive memory and computing architectures, e.g., in-memory computing and neuromorphics.

physics.app-ph↗

arXiv2017

Classification of entities via their descriptive sentences

Hypernym identification of open-domain entities is crucial for taxonomy construction as well as many higher-level applications. Current methods suffer from either low precision or low recall. To decrease the difficulty of this problem, we adopt a classification-based method. We pre-define a concept taxonomy and classify an entity to one of its leaf concept, based on the name and description information of the entity. A convolutional neural network classifier and a K-means clustering module are adopted for classification. We applied this system to 2.1 million Baidu Baike entities, and 1.1 million of them were successfully identified with a precision of 99.36%.

cs.AI↗

arXiv2017

Deterministic switching of perpendicularly magnetic layers by spin orbital torque through stray field engineering

We proposed a novel multilayer structure to realize the deterministic switching of perpendicularly magnetized layers by spin orbital torque from the spin Hall effect through stray field engineering. In our design, a pinned magnetic layer is introduced under the heave metal separated by an insulator, generating an in-plane stray field in the perpendicularly magnetized layer. We have confirmed the deterministic switching of perpendicularly magnetized layers through micromagnetic simulation and theoretical analysis. The in-plane stray field accounts for the deterministic switching exhibited in the structure and the reversal ultimate state of the magnetic layer is predictable when the applied spin current density is above the critical spin current density. Moreover, the stray field is easily tunable in a wide range by adjusting the saturation magnetization and dimensions of the pinned layer, and can accommodate different perpendicularly magnetized materials without any external magnetic field.

physics.app-ph↗

arXiv2017

De-identification of medical records using conditional random fields and long short-term memory networks

The CEGS N-GRID 2016 Shared Task 1 in Clinical Natural Language Processing focuses on the de-identification of psychiatric evaluation records. This paper describes two participating systems of our team, based on conditional random fields (CRFs) and long short-term memory networks (LSTMs). A pre-processing module was introduced for sentence detection and tokenization before de-identification. For CRFs, manually extracted rich features were utilized to train the model. For LSTMs, a character-level bi-directional LSTM network was applied to represent tokens and classify tags for each token, following which a decoding layer was stacked to decode the most probable protected health information (PHI) terms. The LSTM-based system attained an i2b2 strict micro-F_1 measure of 89.86%, which was higher than that of the CRF-based system.

cs.CL↗

arXiv2017

EMR-based medical knowledge representation and inference via Markov random fields and distributed representation learning

Objective: Electronic medical records (EMRs) contain an amount of medical knowledge which can be used for clinical decision support (CDS). Our objective is a general system that can extract and represent these knowledge contained in EMRs to support three CDS tasks: test recommendation, initial diagnosis, and treatment plan recommendation, with the given condition of one patient. Methods: We extracted four kinds of medical entities from records and constructed an EMR-based medical knowledge network (EMKN), in which nodes are entities and edges reflect their co-occurrence in a single record. Three bipartite subgraphs (bi-graphs) were extracted from the EMKN to support each task. One part of the bi-graph was the given condition (e.g., symptoms), and the other was the condition to be inferred (e.g., diseases). Each bi-graph was regarded as a Markov random field to support the inference. Three lazy energy functions and one parameter-based energy function were proposed, as well as two knowledge representation learning-based energy functions, which can provide a distributed representation of medical entities. Three measures were utilized for performance evaluation. Results: On the initial diagnosis task, 80.11% of the test records identified at least one correct disease from top 10 candidates. Test and treatment recommendation results were 87.88% and 92.55%, respectively. These results altogether indicate that the proposed system outperformed the baseline methods. The distributed representation of medical entities does reflect similarity relationships in regards to knowledge level. Conclusion: Combining EMKN and MRF is an effective approach for general medical knowledge representation and inference. Different tasks, however, require designing their energy functions individually.

cs.AI↗

arXiv2017

Constructing a Hierarchical User Interest Structure based on User Profiles

The interests of individual internet users fall into a hierarchical structure which is useful in regards to building personalized searches and recommendations. Most studies on this subject construct the interest hierarchy of a single person from the document perspective. In this study, we constructed the user interest hierarchy via user profiles. We organized 433,397 user interests, referred to here as "attentions", into a user attention network (UAN) from 200 million user profiles; we then applied the Louvain algorithm to detect hierarchical clusters in these attentions. Finally, a 26-level hierarchy with 34,676 clusters was obtained. We found that these attention clusters were aggregated according to certain topics as opposed to the hyponymy-relation based conceptual ontologies. The topics can be entities or concepts, and the relations were not restrained by hyponymy. The concept relativity encapsulated in the user's interest can be captured by labeling the attention clusters with corresponding concepts.

cs.CL↗

arXiv2017

Learning and inference in knowledge-based probabilistic model for medical diagnosis

Based on a weighted knowledge graph to represent first-order knowledge and combining it with a probabilistic model, we propose a methodology for the creation of a medical knowledge network (MKN) in medical diagnosis. When a set of symptoms is activated for a specific patient, we can generate a ground medical knowledge network composed of symptom nodes and potential disease nodes. By Incorporating a Boltzmann machine into the potential function of a Markov network, we investigated the joint probability distribution of the MKN. In order to deal with numerical symptoms, a multivariate inference model is presented that uses conditional probability. In addition, the weights for the knowledge graph were efficiently learned from manually annotated Chinese Electronic Medical Records (CEMRs). In our experiments, we found numerically that the optimum choice of the quality of disease node and the expression of symptom variable can improve the effectiveness of medical diagnosis. Our experimental results comparing a Markov logic network and the logistic regression algorithm on an actual CEMR database indicate that our method holds promise and that MKN can facilitate studies of intelligent diagnosis.

cs.AI↗

arXiv2015

Symmetric Ternary Quantum Homomorphic Encryption Schemes Based on the Ternary Quantum One-Time Pad

Aiming at a ternary quantum logic circuit, four symmetric ternary quantum homomorphic encryption schemes, based on ternary quantum one-time protocol, were presented. First, for a one-qutrit rotation gate, a homomorphic quantum encryption scheme was constructed. Second, in view of the synthesis of a 3x3 general unitary transformation, another one-qutrit quantum homomorphic encryption scheme was proposed. Third, according to the one-qutrit scheme, the two-qutrit quantum homomorphic encryption scheme about GCX(m') gate was constructed and was further generalized to the n-qutrit unitary matrix case. Finally, the security of these schemes was analyzed from two perspectives. It could be concluded that the attacker can correctly guess the encryption key with a maximum probability ${p_k} = {1 \mathord{\left/ {\vphantom {1 {3^{3n}}}} \right. \kern-\nulldelimiterspace} {3^{3n}}}$, thus it can better protect the privacy of users' data. Moreover these schemes can be well integrated into future quantum remote server architecture, and the computational security of the user's private quantum information can be well solved in a distributed computing environment.

quant-ph↗