Search

Aspect-based sentiment analysis (ABSA) identifies sentiment information related to specific aspects and provides deeper market insights to businesses and organizations. With the emergence of large language models (LMs), recent studies have proposed using fixed examples for instruction tuning to reformulate ABSA as a generation task. However, the performance is sensitive to the selection of in-context examples; several retrieval methods are based on surface similarity and are independent of the LM generative objective. This study proposes an instruction learning method with retrieval-based example ranking for ABSA tasks. For each target sample, an LM was applied as a scorer to estimate the likelihood of the output given the input and a candidate example as the prompt, and training examples were labeled as positive or negative by ranking the scores. An alternating training schema is proposed to train both the retriever and LM. Instructional prompts can be constructed using high-quality examples. The LM is used for both scoring and inference, improving the generation efficiency without incurring additional computational costs or training difficulties. Extensive experiments on three ABSA subtasks verified the effectiveness of the proposed method, demonstrating its superiority over various strong baseline models. Code and data are released at https://github.com/zgMin/IT-RER-ABSA., Comment: ACL Findings 2024

Azimuthal anisotropy has been ubiquitously observed in high-energy proton-proton, proton-nucleus, and nucleus-nucleus (heavy-ion) collisions, shaking the early belief that those anisotropies must stem from utterly strong interactions. This work reports a study of anisotropic expansion of cold $^{6}$Li Fermi gases, initially trapped in an anisotropic potential, as a function of the interaction strength that can be readily tuned by an external magnetic field. It is found that the expansion anisotropy builds up quickly at small interaction strength, without the need of utterly strong interactions. A universal behavior of the expansion anisotropy is quantitatively observed between cold-atom and heavy-ion systems, despite their vast differences in physics. This universality will potentially unify a variety of disciplines in nature, from the weakly interacting dilute systems of gases to the strongly interacting quark-gluon plasma of the early universe., Comment: 10 pages, 11 figures

The pre-training for language models captures general language understanding but fails to distinguish the affective impact of a particular context to a specific word. Recent works have sought to introduce contrastive learning (CL) for sentiment-aware pre-training in acquiring affective information. Nevertheless, these methods present two significant limitations. First, the compatibility of the GPU memory often limits the number of negative samples, hindering the opportunities to learn good representations. In addition, using only a few sentiment polarities as hard labels, e.g., positive, neutral, and negative, to supervise CL will force all representations to converge to a few points, leading to the issue of latent space collapse. This study proposes a soft momentum contrastive learning (SoftMCL) for fine-grained sentiment-aware pre-training. Instead of hard labels, we introduce valence ratings as soft-label supervision for CL to fine-grained measure the sentiment similarities between samples. The proposed SoftMCL is conducted on both the word- and sentence-level to enhance the model's ability to learn affective information. A momentum queue was introduced to expand the contrastive samples, allowing storing and involving more negatives to overcome the limitations of hardware platforms. Extensive experiments were conducted on four different sentiment-related tasks, which demonstrates the effectiveness of the proposed SoftMCL method. The code and data of the proposed SoftMCL is available at: https://www.github.com/wangjin0818/SoftMCL/., Comment: Accepted by LREC-COLING 2024

We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. HyperCLOVA X was trained on a balanced mix of Korean, English, and code data, followed by instruction-tuning with high-quality human-annotated datasets while abiding by strict safety guidelines reflecting our commitment to responsible AI. The model is evaluated across various benchmarks, including comprehensive reasoning, knowledge, commonsense, factuality, coding, math, chatting, instruction-following, and harmlessness, in both Korean and English. HyperCLOVA X exhibits strong reasoning capabilities in Korean backed by a deep understanding of the language and cultural nuances. Further analysis of the inherent bilingual nature and its extension to multilingualism highlights the model's cross-lingual proficiency and strong generalization ability to untargeted languages, including machine translation between several language pairs and cross-lingual inference tasks. We believe that HyperCLOVA X can provide helpful guidance for regions or countries in developing their sovereign LLMs., Comment: 44 pages; updated authors list and fixed author names

Effectively and efficiently adapting a pre-trained language model (PLM) for human-centered text understanding (HCTU) is challenging since user tokens are million-level in most personalized applications and do not have concrete explicit semantics. A standard and parameter-efficient approach (e.g., LoRA) necessitates memorizing numerous suits of adapters for each user. In this work, we introduce a personalized LoRA (PLoRA) with a plug-and-play (PnP) framework for the HCTU task. PLoRA is effective, parameter-efficient, and dynamically deploying in PLMs. Moreover, a personalized dropout and a mutual information maximizing strategies are adopted and hence the proposed PLoRA can be well adapted to few/zero-shot learning scenarios for the cold-start issue. Experiments conducted on four benchmark datasets show that the proposed method outperforms existing methods in full/few/zero-shot learning scenarios for the HCTU task, even though it has fewer trainable parameters. For reproducibility, the code for this paper is available at: https://github.com/yoyo-yun/PLoRA., Comment: Accepted by AAAI 2024

In this work the production of exotic hadron $\rm X(3872)$ in $pp$ collisions at $\sqrt{s}=2.76\,\mathrm{TeV}$ is investigated by the parton and hadron cascade model {\footnotesize PACIAE 3.0}. We firstly use the model to generated, respectively, the final partonic state (Quark Phase Space, QPS) and the final hadronic state (Hadron Phase Space, HPS). The $\rm X(3872)$ tetraquark state and molecular state are then investigated with the quantum statistical mechanics inspired dynamically constrained phase-space coalescence model in the QPS and HPS, respectively. The simulated results of their yields, rapidity distributions, and transverse momentum spectra show a signifcant discrepancy between the $\rm X(3872)$ tetraquark state and the molecular state. Each of these observables may serve as a criterion to identify the $\rm X(3872)$ as either the molecular state or the compact tetraquark state., Comment: 7 pages, 6 figures

Within an isospin- and momentum-dependent transport model by including the kaon production, we study the kaon prodution in heavy-ion collisions (HICs) at SIS (Darmstadt Schwerionen Synchrotron, GSI) energies. Based on simulations of a centrality of 0-40\% Au + Au collision at $\sqrt{s_{NN}}=2.4$ GeV, a typical reaction that has been carried out by the HADES Collaborator, we find that the medium modification of kaon masses plays a vital role in studying the kaon productions in HICs, and is also unavoidable for the successful interpretation of the HADES data on kaon rapidity distributions and transverse mass spectra. Moreover, we also find that the kaon transverse and directed flows are affected significantly by both the kaon potential or dispersion relation and medium modification of kaon masses, and thus could be used in HICs as the sensitive probes to detect the kaon potential or dispersion relation as well as the medium modification of kaon masses., Comment: 8 pages, 6 figures, submitted for publication

This paper features an analog of Sanov's theorem for finite-state Markov chains indexed by rooted d-trees, obtained via the method of types in the classical analysis of large deviations. Along with the theorem comes two applications: an almost-sure type convergence of sample means and a formula for the Hausdorff dimension of the symbolic space associated with the irreducible Markov chain.

We prove a van der Corput lemma for non-atomic self-similar measures $\mu$. As an application, we show that the correlations of all finite orders of $( x^n \mod 1 )_{n\geq 1}$ converge to the Poissonian model for $\mu$-a.e. $x$, assuming $x>1$. We also complete a recent result of Algom, Rodriguez Hertz, and Wang (obtained simultaneously by Baker and Banaji), showing that any self-conformal measure with respect to a non-affine real analytic IFS has polynomial Fourier decay.

In this work we investigate the $J/\psi$ production in proton-proton collisions at the center-of-mass energy ($\sqrt{s}$) equal to 2.76, 5.02, 7, 8 and 13 TeV with a parton and hadron cascade model PACIAE 2.2a. It is based on PYTHIA but extended considering the partonic and hadronic rescatterings before and after hadronization, respectively. In the PYTHIA sector the $J/\psi$ production quantum chromodynamics processes are selected specially and a bias factor is proposed correspondingly. The calculated total cross sections, the differential cross sections as a function of the transverse momentum and the rapidity of $J/\psi$ in the forward rapidity region reproduce the corresponding experimental measurements reasonably well. In the mid-rapidity region, the double differential cross sections at $\sqrt{s}=$ 5.02, 7 and 13 TeV are also in a good agreement with the experimental data. Moreover, we interpolate the double differential cross section as well as the total cross section of $J/\psi$ in the mid-rapidity region at $\sqrt{s}=$ 8 TeV, which could be validated if the experimental data is available., Comment: 6 pages, 8 figures, 3 tables, accepted by Phys. Rev. C

This article investigates the topological pressure of isotropic axial products of Markov subshift on the $d$-tree. We show that the quantity increases with dimension $d$, and demonstrate that, with the introduction of surface pressure, the two types of pressure admit the same asymptotic value. To this end, the pattern distribution vectors and the associated transition matrices are introduced herein to partially transplant the large deviation theory to tree-shifts, and so the increasing property is proved via an almost standard argument. An application of the main result to a wider class of shift spaces is also provided in this paper, and numerical experiments are included for the purpose of verification.

In recent decades, traditional drug research and development have been facing challenges such as high cost, long timelines, and high risks. To address these issues, many computational approaches have been suggested for predicting the relationship between drugs and diseases through drug repositioning, aiming to reduce the cost, development cycle, and risks associated with developing new drugs. Researchers have explored different computational methods to predict drug-disease associations, including drug side effects-disease associations, drug-target associations, and miRNAdisease associations. In this comprehensive review, we focus on recent advances in predicting drug-disease association methods for drug repositioning. We first categorize these methods into several groups, including neural network-based algorithms, matrixbased algorithms, recommendation algorithms, link-based reasoning algorithms, and text mining and semantic reasoning. Then, we compare the prediction performance of existing drug-disease association prediction algorithms. Lastly, we delve into the present challenges and future prospects concerning drug-disease associations., Comment: 34 page, 5 figures, 2 tables

We introduce a parton and hadron cascade model PACIAE 3.0 based on PYTHIA 6.428 and the PACIAE 2.2 program series. The simulation framework of C-, B-, and A-loops are designed for the high energy ($\sqrt{s_{NN}}\geq 3$ GeV) and low energy ($\sqrt{s_{NN}}<3$ GeV) nuclear collisions, respectively, in PACIAE 3.0. In the C-loop simulation, the parton-parton inelastic scattering processes are added in the partonic rescattering process. The single string structure and multiple string interaction mechanism have been introduced investigating the strangeness enhancement in C- and B-loop. An improved mapping relation between the centrality percentage definition and the impact parameter definition is proposed responding the observation of $b_{max}\approx 20$ fm from ALICE, ATLAS, and CMS collaborations. We have extensively modified the phenomenological coalescence hadronization model. The PACIAE 3.0 model simulated results of particle yield, transverse momentum distribution, and rapidity distribution well reproduce, respectively, the experimental data measured at FOPI, E895, RHIC, and LHC energies., Comment: 15 pages, 15 figures

Machine Learning (ML) methods and tools have gained great success in many data, signal, image and video processing tasks, such as classification, clustering, object detection, semantic segmentation, language processing, Human-Machine interface, etc. In computer vision, image and video processing, these methods are mainly based on Neural Networks (NN) and in particular Convolutional NN (CNN), and more generally Deep NN. Inverse problems arise anywhere we have indirect measurement. As, in general, those inverse problems are ill-posed, to obtain satisfactory solutions for them needs prior information. Different regularization methods have been proposed, where the problem becomes the optimization of a criterion with a likelihood term and a regularization term. The main difficulty, however, in great dimensional real applications, remains the computational cost. Using NN, and in particular Deep Learning (DL) surrogate models and approximate computation, can become very helpful. In this work, we focus on NN and DL particularly adapted for inverse problems. We consider two cases: First the case where the forward operator is known and used as physics constraint, the second more general data driven DL methods., Comment: arXiv admin note: text overlap with arXiv:2308.15492

Inverse problems arise anywhere we have indirect measurement. As, in general they are ill-posed, to obtain satisfactory solutions for them needs prior knowledge. Classically, different regularization methods and Bayesian inference based methods have been proposed. As these methods need a great number of forward and backward computations, they become costly in computation, in particular, when the forward or generative models are complex and the evaluation of the likelihood becomes very costly. Using Deep Neural Network surrogate models and approximate computation can become very helpful. However, accounting for the uncertainties, we need first understand the Bayesian Deep Learning and then, we can see how we can use them for inverse problems. In this work, we focus on NN, DL and more specifically the Bayesian DL particularly adapted for inverse problems. We first give details of Bayesian DL approximate computations with exponential families, then we will see how we can use them for inverse problems. We consider two cases: First the case where the forward operator is known and used as physics constraint, the second more general data driven DL methods. keyword: Neural Network, Variational Bayesian inference, Bayesian Deep Learning (DL), Inverse problems, Physics based DL., Comment: Presented at MaxEnt 2023: International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering, Max Planck Institut, Garching, Germany, July 3-7, 2023. A modified version to appear in MaxEnt2023 Proceedings, published by MDPI

Quasicrystals allow for symmetries that are impossible in crystalline materials, such as eight-fold rotational symmetry, enabling the existence of novel higher-order topological insulators in two dimensions without crystalline counterparts. However, it remains an open question whether three-dimensional higher-order topological insulators and Weyl-like semimetals without crystalline counterparts can exist. Here, we demonstrate the existence of a second-order topological insulator by constructing and exploring a three-dimensional model Hamiltonian in a stack of Ammann-Beenker tiling quasicrystalline lattices. The topological phase has eight chiral hinge modes that lead to quantized longitudinal conductances of $4 e^2/h$. We show that the topological phase is characterized by the winding number of the quadrupole moment. We further establish the existence of a second-order topological insulator with time-reversal symmetry, characterized by a $\mathbb{Z}_2$ topological invariant. Finally, we propose a model that exhibits a higher-order Weyl-like semimetal phase, demonstrating both hinge and surface Fermi arcs. Our findings highlight that quasicrystals in three dimensions can give rise to higher-order topological insulators and semimetal phases that are unattainable in crystals., Comment: 7 pages, 6 figures

The quadrupole insulator is a well-known instance of higher-order topological insulators in two dimensions, which possesses midgap corner states in both the energy spectrum and entanglement spectrum. Here, by constructing and exploring a model Hamiltonian under a staggered $\mathbb{Z}_2$ gauge field that respects momentum-glide reflection symmetries, we surprisingly find a quadrupole insulator that lacks zero-energy corner modes in its energy spectrum, despite possessing a nonzero quadrupole moment. Remarkably, the existence of midgap corner modes is found in the entanglement spectrum. Since these midgap states cannot be continuously eliminated, the quadrupole insulator cannot be continuously transformed into a trivial topological insulator, thereby confirming its topological nature. We show that the breakdown of the correspondence between the energy spectrum and entanglement spectrum occurs due to the closure of the edge energy gap when the Hamiltonian is flattened. Finally, we present a model that demonstrates an insulator with corner modes in the energy spectrum even in the absence of the quadrupole moment. In this phase, the entanglement spectrum does not display any midgap states. The results suggest that the bulk-edge correspondence of quadrupole insulators generally manifests in the entanglement spectrum rather than the energy spectrum., Comment: 7 pages, 5 figures

While topological phases have been extensively studied in amorphous systems in recent years, it remains unclear whether the random nature of amorphous materials can give rise to higher-order topological phases that have no crystalline counterparts. Here we theoretically demonstrate the existence of higher-order topological insulators in two-dimensional amorphous systems that can host more than six corner modes, such as eight or twelve corner modes. Although individual sample configuration lacks crystalline symmetry, we find that an ensemble of all configurations exhibits an average crystalline symmetry that provides protection for the new topological phases. To characterize the topological phases, we construct two topological invariants. Even though the bulk energy gap in the topological phase vanishes in the thermodynamic limit, we show that the bulk states near zero energy are localized, as supported by the level-spacing statistics and inverse participation ratio. Our findings open an avenue for exploring average symmetry protected higher-order topological phases in amorphous systems without crystalline counterparts., Comment: 17 pages, 7 figures

Topological phases of matter are classified based on symmetries, with nonsymmorphic symmetries like glide reflections and screw rotations being of particular importance in the classification. In contrast to extensively studied glide reflections in real space, introducing space-dependent gauge transformations can lead to momentum-space glide reflection symmetries, which may even change the fundamental domain for topological classifications, e.g., from a torus to a Klein bottle. Here we discover a new class of three-dimensional (3D) higher-order topological insulators, protected by a pair of momentum-space glide reflections. It supports gapless hinge modes, as dictated by the quadrupole moment and Wannier Hamiltonians defined on a Klein bottle manifold, and we introduce two topological invariants to characterize this phase. Our predicted topological hinge modes are experimentally verified in a 3D-printed acoustic crystal, providing direct evidence for 3D higher-order Klein bottle topological insulators. Our results not only showcase the remarkable role of momentum-space glide reflections in topological classifications, but also pave the way for experimentally exploring physical effects arising from momentum-space nonsymmorphic symmetries., Comment: 37 pages, 14 figures

Road extraction is a process of automatically generating road maps mainly from satellite images. Existing models all target to generate roads from the scratch despite that a large quantity of road maps, though incomplete, are publicly available (e.g. those from OpenStreetMap) and can help with road extraction. In this paper, we propose to conduct road extraction based on satellite images and partial road maps, which is new. We then propose a two-branch Partial to Complete Network (P2CNet) for the task, which has two prominent components: Gated Self-Attention Module (GSAM) and Missing Part (MP) loss. GSAM leverages a channel-wise self-attention module and a gate module to capture long-range semantics, filter out useless information, and better fuse the features from two branches. MP loss is derived from the partial road maps, trying to give more attention to the road pixels that do not exist in partial road maps. Extensive experiments are conducted to demonstrate the effectiveness of our model, e.g. P2CNet achieves state-of-the-art performance with the IoU scores of 70.71% and 75.52%, respectively, on the SpaceNet and OSM datasets., Comment: This paper has been accepted by IEEE Transactions on Geoscience and Remote Sensing