arXiv subjects

Hu Xu

Publications and source records attributed to Hu Xu.

At least 91 records · Page 5Linked to original sources

arXiv2019

Controlled CNN-based Sequence Labeling for Aspect Extraction

One key task of fine-grained sentiment analysis on reviews is to extract aspects or features that users have expressed opinions on. This paper focuses on supervised aspect extraction using a modified CNN called controlled CNN (Ctrl). The modified CNN has two types of control modules. Through asynchronous parameter updating, it prevents over-fitting and boosts CNN's performance significantly. This model achieves state-of-the-art results on standard aspect extraction datasets. To the best of our knowledge, this is the first paper to apply control modules to aspect extraction.

cs.CL↗

arXiv2019

Rational design principles of quantum anomalous Hall effect from superlattice-like magnetic topological insulators

As one of paradigmatic phenomena in condensed matter physics, the quantum anomalous Hall effect (QAHE) in stoichiometric Chern insulators has drawn great interest for years. By using model Hamiltonian analysis and first-principle calculations, we establish a topological phase diagram and map on it with different two-dimensional configurations, which is taken from the recently-grown magnetic topological insulators MnBi4Te7 and MnBi6Te10 with superlattice-like stacking patterns. These configurations manifest various topological phases, including quantum spin Hall effect with and without time-reversal symmetry, as well as QAHE. We then provide design principles to trigger QAHE by tuning experimentally accessible knobs, such as slab thickness and magnetization. Our work reveals that superlattice-like magnetic topological insulators with tunable exchange interaction serve as an ideal platform to realize the long-sought QAHE in pristine compounds, paving a new avenue within the area of topological materials.

cond-mat.mes-hall↗

arXiv2019

BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis

Question-answering plays an important role in e-commerce as it allows potential customers to actively seek crucial information about products or services to help their purchase decision making. Inspired by the recent success of machine reading comprehension (MRC) on formal documents, this paper explores the potential of turning customer reviews into a large source of knowledge that can be exploited to answer user questions.~We call this problem Review Reading Comprehension (RRC). To the best of our knowledge, no existing work has been done on RRC. In this work, we first build an RRC dataset called ReviewRC based on a popular benchmark for aspect-based sentiment analysis. Since ReviewRC has limited training examples for RRC (and also for aspect-based sentiment analysis), we then explore a novel post-training approach on the popular language model BERT to enhance the performance of fine-tuning of BERT for RRC. To show the generality of the approach, the proposed post-training is also applied to some other review-based tasks such as aspect extraction and aspect sentiment classification in aspect-based sentiment analysis. Experimental results demonstrate that the proposed post-training is highly effective. The datasets and code are available at https://www.cs.uic.edu/~hxu/.

cs.CL↗

arXiv2019

Open-world Learning and Application to Product Classification

Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training. However, in the dynamic world, new or unseen class examples may appear constantly. A model working in such an environment must be able to reject unseen classes (not seen or used in training). If enough data is collected for the unseen classes, the system should incrementally learn to accept/classify them. This learning paradigm is called open-world learning (OWL). Existing OWL methods all need some form of re-training to accept or include the new classes in the overall model. In this paper, we propose a meta-learning approach to the problem. Its key novelty is that it only needs to train a meta-classifier, which can then continually accept new classes when they have enough labeled data for the meta-classifier to use, and also detect/reject future unseen classes. No re-training of the meta-classifier or a new overall classifier covering all old and new classes is needed. In testing, the method only uses the examples of the seen classes (including the newly added classes) on-the-fly for classification and rejection. Experimental results demonstrate the effectiveness of the new approach.

cs.CL↗

arXiv2019

Symmetry-assisted protection and compensation of hidden spin polarization in centrosymmetric systems

It is recently noted that in certain centrosymmetric compounds, spin-orbit interaction couples each local sector that lacks inversion symmetry and thus leads to visible spin polarization effects in the real space, dubbed as 'hidden spin polarization (HSP)'. However, observable spin polarization of a given local sector suffers interference by its inversion partner, impeding material realization and potential applications of HSP. Starting from a single-orbital tight-binding model, we propose a nontrivial way to protect strong sector-projected spin texture through minimizing the interaction between inversion partners by nonsymmorphic symmetry. The HSP effect is generally compensated by inversion partners near the Γ point but immune from interaction around the boundary of the Brillouin zone. We further summarize 17 layer groups that support such symmetry-assisted HSP and identify by first-principle calculations hundreds of quasi-2D materials from the existing databases, among which a group of rare-earth compounds LnOI (Ln = Pr, Nd, Ho, Tm and Lu) serves as great candidates showing strong Rashba- and Dresselhaus-type HSP. Our finding also provides an ideal platform to control HSP for emergent physical effects, such as opening a hybridization gap by tensile strain to realize the time-reversal-invariant topological superconductivity.

cond-mat.mes-hall↗

arXiv2018

Recipe for Dirac Phonon States with Quantized Valley Berry Phase in Two Dimensional Hexagonal Lattices

The topological quantum states in two-dimensional (2D) materials are fascinating subjects of research, which usually highlight electron-related systems. In this work, we present a recipe that leads to Dirac phonon states with quantized valley Berry phase in 2D hexagonal lattices by first-principles calculations. We show that candidates possessing the three-fold rotational symmetry at the corners of the hexagonal Brillouin zone host valley Dirac phonons, which are guaranteed to remain intact with respect to perturbations. We identify that such special topological features populated by Dirac phonons can be realized in various 2D materials. In particular, the monolayer CrI$_3$, an attractive 2D magnetic semiconductor with exotic applications in spintronics, is an ideal platform to investigate nontrivial phonons in experiments. We further confirm that the phonon Berry phase is quantized to $\pm π$ at two inequivalent valleys. The phonon edge states terminated at the projection of phonon Dirac cones are clearly visible. This work demonstrates that 2D hexagonal lattices with attractive valley Dirac phonons will extend the knowledge of valley physics, providing wide applications of topological phonons.

cond-mat.mes-hall↗

arXiv2018

Large Band Gap Quantum Anomalous Hall Phase in Hexagonal Organometallic Frameworks

The nontrivial band gap plays a critical role in quantum anomalous Hall (QAH) insulators. In this work, we propose that the intrinsic QAH phase with sizable band gaps up to 367 meV is achieved in two-dimensional hexagonal organometallic frameworks (HOMFs). Based on first-principles calculations and effective model analysis, we uncover that these large band gaps in transition metal based HOMFs are opened by strong spin-orbital coupling of the localized 4d or 5d electrons. Importantly, we reveal that Coulomb correlations can further significantly enhance the nontrivial band gaps. In addition, we suggest a possible avenue to grow these organometallic QAH insulators on a semiconducting SiC(111) substrate, and the topological features are perfectly preserved due to the van der Waals interaction. Our work shows that the correlation remarkably enhances the nontrivial band gaps, providing exotic candidates to realize the QAH states at high temperatures.

cond-mat.mes-hall↗

arXiv2018

Insights into the Unusual Semiconducting Behavior in Low-Dimensional Boron

Elementary semiconductors are rare and attractive, especially for low-dimensional materials. Unfortunately, most of boron nanostructures were found to be metallic, despite of their typical semiconducting bulk structure. Herein, we propose a general recipe to realize low-dimensional semiconducting boron. This unusual semiconducting behavior is attributed to charge transfer and electron localization, induced by the symmetry breaking that divides boron atoms into cations and anions. In addition, it is feasible to accomplish band gap engineering by rationally designing various structures. Importantly, the low-dimensional semiconducting boron are predicted to be an excellent solar-cell material with the power conversion efficiency of higher than 20%, paving the way for their promising optoelectronic applications.

cond-mat.mes-hall↗

arXiv2018

Lifelong Domain Word Embedding via Meta-Learning

Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks. General-purpose embeddings trained on large-scale corpora are often sub-optimal for domain-specific applications. However, domain-specific tasks often do not have large in-domain corpora for training high-quality domain embeddings. In this paper, we propose a novel lifelong learning setting for domain embedding. That is, when performing the new domain embedding, the system has seen many past domains, and it tries to expand the new in-domain corpus by exploiting the corpora from the past domains via meta-learning. The proposed meta-learner characterizes the similarities of the contexts of the same word in many domain corpora, which helps retrieve relevant data from the past domains to expand the new domain corpus. Experimental results show that domain embeddings produced from such a process improve the performance of the downstream tasks.

cs.CL↗

arXiv2018

Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction

One key task of fine-grained sentiment analysis of product reviews is to extract product aspects or features that users have expressed opinions on. This paper focuses on supervised aspect extraction using deep learning. Unlike other highly sophisticated supervised deep learning models, this paper proposes a novel and yet simple CNN model employing two types of pre-trained embeddings for aspect extraction: general-purpose embeddings and domain-specific embeddings. Without using any additional supervision, this model achieves surprisingly good results, outperforming state-of-the-art sophisticated existing methods. To our knowledge, this paper is the first to report such double embeddings based CNN model for aspect extraction and achieve very good results.

cs.CL↗

arXiv2018

Turning Copper Metal into Weyl Semimetal

A search for new topological quantum systems is challenging due to the requirement of non{trivial band connectivity that leads to protected surface states of electrons. A progress in this field was primarily due to a realization of band inversion mechanism between even and odd parity states that was proven to be very useful in both predicting many of such systems and our understanding their topological properties. Despite many proposed materials assume the band inversion between s and p (or p/d, d/f) electrons, here, we explore a different mechanism where the occupied d states subjected to a tetrahedral crystal field produce an active t2g manifold behaving as a state with an effective orbital momentum equal to negative one, and pushing jeff = 1=2 doublet at a higher energy. Via hybridization with nearest neighbor orbitals realizable, e.g., in a zincblende structural environment, this allows a formation of odd parity state whose subsequent band inversion with an unoccupied s band becomes possible, prompting us to look for the compounds with Cu+1 ionic state. Chemical valence arguments coupled to a search in materials database lead us to systematically investigate electronic structures and topological properties of CuY (Y=F, Cl, Br, I) and CuXO (X=Li, Na, K, Rb) families of compounds. Our theoretical results show that CuF displays a behavior characteristic of an ideal Weyl semimetal with 24 Weyl nodes at the bulk Brillouin Zone. We also find that another compounds CuNaO and CuLiO are the s-d inversion type topological insulators. Results for their electronic structures and corresponding surfaces states are presented and discussed in the context of their topological properties.

cond-mat.mtrl-sci↗

arXiv2018

Unseen Class Discovery in Open-world Classification

This paper concerns open-world classification, where the classifier not only needs to classify test examples into seen classes that have appeared in training but also reject examples from unseen or novel classes that have not appeared in training. Specifically, this paper focuses on discovering the hidden unseen classes of the rejected examples. Clearly, without prior knowledge this is difficult. However, we do have the data from the seen training classes, which can tell us what kind of similarity/difference is expected for examples from the same class or from different classes. It is reasonable to assume that this knowledge can be transferred to the rejected examples and used to discover the hidden unseen classes in them. This paper aims to solve this problem. It first proposes a joint open classification model with a sub-model for classifying whether a pair of examples belongs to the same or different classes. This sub-model can serve as a distance function for clustering to discover the hidden classes of the rejected examples. Experimental results show that the proposed model is highly promising.

cs.LG↗

arXiv2017

Dual Attention Network for Product Compatibility and Function Satisfiability Analysis

Product compatibility and their functionality are of utmost importance to customers when they purchase products, and to sellers and manufacturers when they sell products. Due to the huge number of products available online, it is infeasible to enumerate and test the compatibility and functionality of every product. In this paper, we address two closely related problems: product compatibility analysis and function satisfiability analysis, where the second problem is a generalization of the first problem (e.g., whether a product works with another product can be considered as a special function). We first identify a novel question and answering corpus that is up-to-date regarding product compatibility and functionality information. To allow automatic discovery product compatibility and functionality, we then propose a deep learning model called Dual Attention Network (DAN). Given a QA pair for a to-be-purchased product, DAN learns to 1) discover complementary products (or functions), and 2) accurately predict the actual compatibility (or satisfiability) of the discovered products (or functions). The challenges addressed by the model include the briefness of QAs, linguistic patterns indicating compatibility, and the appropriate fusion of questions and answers. We conduct experiments to quantitatively and qualitatively show that the identified products and functions have both high coverage and accuracy, compared with a wide spectrum of baselines.

cs.CL↗

arXiv2017

Product Function Need Recognition via Semi-supervised Attention Network

Functionality is of utmost importance to customers when they purchase products. However, it is unclear to customers whether a product can really satisfy their needs on functions. Further, missing functions may be intentionally hidden by the manufacturers or the sellers. As a result, a customer needs to spend a fair amount of time before purchasing or just purchase the product on his/her own risk. In this paper, we first identify a novel QA corpus that is dense on product functionality information \footnote{The annotated corpus can be found at \url{https://www.cs.uic.edu/~hxu/}.}. We then design a neural network called Semi-supervised Attention Network (SAN) to discover product functions from questions. This model leverages unlabeled data as contextual information to perform semi-supervised sequence labeling. We conduct experiments to show that the extracted function have both high coverage and accuracy, compared with a wide spectrum of baselines.

cs.CL↗

arXiv2017

DOC: Deep Open Classification of Text Documents

Traditional supervised learning makes the closed-world assumption that the classes appeared in the test data must have appeared in training. This also applies to text learning or text classification. As learning is used increasingly in dynamic open environments where some new/test documents may not belong to any of the training classes, identifying these novel documents during classification presents an important problem. This problem is called open-world classification or open classification. This paper proposes a novel deep learning based approach. It outperforms existing state-of-the-art techniques dramatically.

cs.CL↗

arXiv2017

Two-Dimensional Semiconducting Boron Monolayers

The two-dimensional boron monolayers were reported to be metallic both in previous theoretical predictions and experimental observations, however, we have firstly found a family of boron monolayers with the novel semiconducting property as confirmed by the first-principles calculations with the quasi-particle G0W0 approach. We demonstrate that the vanished metallicity characterized by the pz-derived bands cross the Fermi level is attributed to the motif of a triple-hexagonal-vacancy, with which various semiconducting boron monolayers are designed to realize the band-gap engineering for the potential applications in electronic devices. The semiconducting boron monolayers in our predictions are expected to be synthesized on the proper substrates, due to the similar stabilities to the ones observed experimentally.

cond-mat.mtrl-sci↗

arXiv2017

Supervised Complementary Entity Recognition with Augmented Key-value Pairs of Knowledge

Extracting opinion targets is an important task in sentiment analysis on product reviews and complementary entities (products) are one important type of opinion targets that may work together with the reviewed product. In this paper, we address the problem of Complementary Entity Recognition (CER) as a supervised sequence labeling with the capability of expanding domain knowledge as key-value pairs from unlabeled reviews, by automatically learning and enhancing knowledge-based features. We use Conditional Random Field (CRF) as the base learner and augment CRF with knowledge-based features (called the Knowledge-based CRF or KCRF for short). We conduct experiments to show that KCRF effectively improves the performance of supervised CER task.

cs.CL↗

arXiv2017

One-dimensional phosphorus chain and two-dimensional blue phosphorene grown on Au(111) by molecular-beam epitaxy

Single layer (SL) phosphorus (phosphorene) has drawn considerable research attention recently as a two-dimensional (2D) material for application promises. It is a semiconductor showing superior transport and optical properties. Few-layer or SL black phosphorus has been successfully isolated by exfoliation from bulk crystals and extensively studied thereof for its electronic and optical properties. Blue phosphorus (blueP), an allotrope of black phosphorus where atoms are arranged in a more flat atomic configuration, has been recently suggested by theory to exist in the SL form on some substrates. In this work, we report the formation of a blueP-like epilayer on Au(111) by molecular-beam epitaxy. In particular, we uncover by scanning tunneling microscopy (STM) one-dimensional (1D) atomic chains at low coverage, which develop into more compact islands or patches of $(\sqrt{3}\times\sqrt{3})R30^\circ$ structure with increasing coverage before blueP-like islands nucleate and grow. We also note an interesting growth characteristic where the $(\sqrt{3}\times\sqrt{3})R30^\circ$ surface at intermediate coverage tends to phase-separate into locally low-coverage 1D chain and high-coverage blueP-like structures, respectively. This experiment thus not only lends a support of the recently proposed half-layer by half-layer (HLBHL) growth mechanism but also reveals the kinetic details of blueP growth processes.

cond-mat.mes-hall↗