arXiv subjects

Jie Yu

Publications and source records attributed to Jie Yu.

At least 91 records · Page 5Linked to original sources

arXiv2023

The Effect of Stellar Contamination on Low-resolution Transmission Spectroscopy: Needs Identified by NASA's Exoplanet Exploration Program Study Analysis Group 21

Study Analysis Group 21 (SAG21) of NASA's Exoplanet Exploration Program Analysis Group (ExoPAG) was organized to study the effect of stellar contamination on space-based transmission spectroscopy, a method for studying exoplanetary atmospheres by measuring the wavelength-dependent radius of a planet as it transits its star. Transmission spectroscopy relies on a precise understanding of the spectrum of the star being occulted. However, stars are not homogeneous, constant light sources but have temporally evolving photospheres and chromospheres with inhomogeneities like spots, faculae, plages, granules, and flares. This SAG brought together an interdisciplinary team of more than 100 scientists, with observers and theorists from the heliophysics, stellar astrophysics, planetary science, and exoplanetary atmosphere research communities, to study the current research needs that can be addressed in this context to make the most of transit studies from current NASA facilities like HST and JWST. The analysis produced 14 findings, which fall into three Science Themes encompassing (1) how the Sun is used as our best laboratory to calibrate our understanding of stellar heterogeneities ("The Sun as the Stellar Benchmark"), (2) how stars other than the Sun extend our knowledge of heterogeneities ("Surface Heterogeneities of Other Stars") and (3) how to incorporate information gathered for the Sun and other stars into transit studies ("Mapping Stellar Knowledge to Transit Studies"). In this invited review, we largely reproduce the final report of SAG21 as a contribution to the peer-reviewed literature.

astro-ph.IM↗

arXiv2023

Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction

Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction. However, these methods tend to ignore the internal information of the Chinese character and cannot filter out the noisy information of external knowledge. To address these issues, we propose a mixture-of-view-experts framework (MoVE) to dynamically learn multi-view features for Chinese relation extraction. With both the internal and external knowledge of Chinese characters, our framework can better capture the semantic information of Chinese characters. To demonstrate the effectiveness of the proposed framework, we conduct extensive experiments on three real-world datasets in distinct domains. Experimental results show consistent and significant superiority and robustness of our proposed framework. Our code and dataset will be released at: https://gitee.com/tmg-nudt/multi-view-of-expert-for-chineserelation-extraction

cs.CL↗

arXiv2023

Behavior Prior Representation learning for Offline Reinforcement Learning

Offline reinforcement learning (RL) struggles in environments with rich and noisy inputs, where the agent only has access to a fixed dataset without environment interactions. Past works have proposed common workarounds based on the pre-training of state representations, followed by policy training. In this work, we introduce a simple, yet effective approach for learning state representations. Our method, Behavior Prior Representation (BPR), learns state representations with an easy-to-integrate objective based on behavior cloning of the dataset: we first learn a state representation by mimicking actions from the dataset, and then train a policy on top of the fixed representation, using any off-the-shelf Offline RL algorithm. Theoretically, we prove that BPR carries out performance guarantees when integrated into algorithms that have either policy improvement guarantees (conservative algorithms) or produce lower bounds of the policy values (pessimistic algorithms). Empirically, we show that BPR combined with existing state-of-the-art Offline RL algorithms leads to significant improvements across several offline control benchmarks. The code is available at \url{https://github.com/bit1029public/offline_bpr}.

cs.LG↗

arXiv2023

Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities using Electrocardiogram Images

The artificial intelligence (AI) system has achieved expert-level performance in electrocardiogram (ECG) signal analysis. However, in underdeveloped countries or regions where the healthcare information system is imperfect, only paper ECGs can be provided. Analysis of real-world ECG images (photos or scans of paper ECGs) remains challenging due to complex environments or interference. In this study, we present an AI system developed to detect and screen cardiac abnormalities (CAs) from real-world ECG images. The system was evaluated on a large dataset of 52,357 patients from multiple regions and populations across the world. On the detection task, the AI system obtained area under the receiver operating curve (AUC) of 0.996 (hold-out test), 0.994 (external test 1), 0.984 (external test 2), and 0.979 (external test 3), respectively. Meanwhile, the detection results of AI system showed a strong correlation with the diagnosis of cardiologists (cardiologist 1 (R=0.794, p<1e-3), cardiologist 2 (R=0.812, p<1e-3)). On the screening task, the AI system achieved AUCs of 0.894 (hold-out test) and 0.850 (external test). The screening performance of the AI system was better than that of the cardiologists (AI system (0.846) vs. cardiologist 1 (0.520) vs. cardiologist 2 (0.480)). Our study demonstrates the feasibility of an accurate, objective, easy-to-use, fast, and low-cost AI system for CA detection and screening. The system has the potential to be used by healthcare professionals, caregivers, and general users to assess CAs based on real-world ECG images.

cs.CV↗

arXiv2023

TESS Asteroseismic Analysis of HD 76920: The Giant Star Hosting An Extremely Eccentric Exoplanet

The Transiting Exoplanet Survey Satellite (TESS) mission searches for new exoplanets. The observing strategy of TESS results in high-precision photometry of millions of stars across the sky, allowing for detailed asteroseismic studies of individual systems. In this work, we present a detailed asteroseismic analysis of the giant star HD 76920 hosting a highly eccentric giant planet ($e = 0.878$) with an orbital period of 415 days, using 5 sectors of TESS light curve that cover around 140 days of data. Solar-like oscillations in HD 76920 are detected around $52 \, μ$Hz by TESS for the first time. By utilizing asteroseismic modeling that takes classical observational parameters and stellar oscillation frequencies as constraints, we determine improved measurements of the stellar mass ($1.22 \pm 0.11\, M_\odot$), radius ($8.68 \pm 0.34\,R_\odot$), and age ($5.2 \pm 1.4\,$Gyr). With the updated parameters of the host star, we update the semi-major axis and mass of the planet as $a=1.165 \pm 0.035$ au and $M_{\rm p}\sin{i} = 3.57 \pm 0.22\,M_{\rm Jup}$. With an orbital pericenter of $0.142 \pm 0.005$ au, we confirm that the planet is currently far away enough from the star to experience negligible tidal decay until being engulfed in the stellar envelope. We also confirm that this event will occur within about 100\,Myr, depending on the stellar model used.

astro-ph.SR↗

arXiv2023

Revised extinctions and radii for 1.5 million stars observed by APOGEE, GALAH, and RAVE

Asteroseismology has become widely accepted as a benchmark for accurate and precise fundamental stellar properties. It can therefore be used to validate and calibrate stellar parameters derived from other approaches. Meanwhile, one can leverage large-volume surveys in photometry, spectroscopy, and astrometry to infer stellar parameters over a wide range of evolutionary stages, independently of asteroseismology. Our pipeline, SEDEX, compares the spectral energy distribution predicted by the MARCS and BOSZ model spectra with 32 photometric bandpasses, combining data from 9 major, large-volume photometric surveys. We restrict the analysis to targets with available spectroscopy from the APOGEE, GALAH, and RAVE surveys to lift the temperature-extinction degeneracy. The cross-survey atmospheric parameter and uncertainty estimates are homogenized with artificial neural networks. Validation of our results with CHARA interferometry, HST CALSPEC spectrophotometry, and asteroseismology, shows that we achieve high precision and accuracy. We present a catalog of improved interstellar extinction ($σ_{A_V} \simeq$ 0.14 mag) and stellar radii ($σ_R/R \simeq$ 7.4\%) for $\sim$1.5 million stars in the low- to high-extinction ($A_V \lesssim 6 $ mag) fields observed by the spectroscopic surveys. We derive global extinctions for 184 Gaia DR2 open clusters, and confirm the differential extinction in NGC 6791 and NGC 6819 that have been subject to extensive asteroseismic analysis. Furthermore, we report 36,854 double-lined spectroscopic main-sequence binary candidates. This catalog will be valuable for providing constraints on detailed modelling of stars and for constructing 3D dust maps of the Kepler field, the TESS CVZs, and the PLATO long duration observation fields.

astro-ph.SR↗

arXiv2022

Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks

Adversarial patch is an important form of real-world adversarial attack that brings serious risks to the robustness of deep neural networks. Previous methods generate adversarial patches by either optimizing their perturbation values while fixing the pasting position or manipulating the position while fixing the patch's content. This reveals that the positions and perturbations are both important to the adversarial attack. For that, in this paper, we propose a novel method to simultaneously optimize the position and perturbation for an adversarial patch, and thus obtain a high attack success rate in the black-box setting. Technically, we regard the patch's position, the pre-designed hyper-parameters to determine the patch's perturbations as the variables, and utilize the reinforcement learning framework to simultaneously solve for the optimal solution based on the rewards obtained from the target model with a small number of queries. Extensive experiments are conducted on the Face Recognition (FR) task, and results on four representative FR models show that our method can significantly improve the attack success rate and query efficiency. Besides, experiments on the commercial FR service and physical environments confirm its practical application value. We also extend our method to the traffic sign recognition task to verify its generalization ability.

cs.CV↗

arXiv2022

Adversarial Sticker: A Stealthy Attack Method in the Physical World

To assess the vulnerability of deep learning in the physical world, recent works introduce adversarial patches and apply them on different tasks. In this paper, we propose another kind of adversarial patch: the Meaningful Adversarial Sticker, a physically feasible and stealthy attack method by using real stickers existing in our life. Unlike the previous adversarial patches by designing perturbations, our method manipulates the sticker's pasting position and rotation angle on the objects to perform physical attacks. Because the position and rotation angle are less affected by the printing loss and color distortion, adversarial stickers can keep good attacking performance in the physical world. Besides, to make adversarial stickers more practical in real scenes, we conduct attacks in the black-box setting with the limited information rather than the white-box setting with all the details of threat models. To effectively solve for the sticker's parameters, we design the Region based Heuristic Differential Evolution Algorithm, which utilizes the new-found regional aggregation of effective solutions and the adaptive adjustment strategy of the evaluation criteria. Our method is comprehensively verified in the face recognition and then extended to the image retrieval and traffic sign recognition. Extensive experiments show the proposed method is effective and efficient in complex physical conditions and has a good generalization for different tasks.

cs.CV↗

arXiv2022

Surface magnetism of rapidly rotating red giants: single versus close binary stars

According to dynamo theory, stars with convective envelopes efficiently generate surface magnetic fields, which manifest as magnetic activity in the form of starspots, faculae, flares, when their rotation period is shorter than their convective turnover time. Most red giants, having undergone significant spin down while expanding, have slow rotation and no spots. However, based on a sample of about 4500 red giants observed by the NASA Kepler mission, a previous study showed that about 8 % display spots, including about 15 % that belong to close binary systems. Here, we shed light on a puzzling fact: for rotation periods less than 80 days, a red giant that belongs to a close binary system displays a photometric modulation about an order of magnitude larger than that of a single red giant with similar rotational period and physical properties. We investigate whether binarity leads to larger magnetic fields when tides lock systems, or if a different spot distribution on single versus close binary stars can explain this fact. For this, we measure the chromospheric emission in the CaII H & K lines of 3130 of the 4465 stars studied in a previous work thanks to the LAMOST survey. We show that red giants in a close-binary configuration with spin-orbit resonance display significantly larger chromospheric emission than single stars, suggesting that tidal locking leads to larger magnetic fields at a fixed rotational period. Beyond bringing interesting new observables to study the evolution of binary systems, this result could be used to distinguish single versus binary red giants in automatic pipelines based on machine learning.

astro-ph.SR↗

arXiv2022

Span-based joint entity and relation extraction augmented with sequence tagging mechanism

Span-based joint extraction simultaneously conducts named entity recognition (NER) and relation extraction (RE) in text span form. However, since previous span-based models rely on span-level classifications, they cannot benefit from token-level label information, which has been proven advantageous for the task. In this paper, we propose a Sequence Tagging augmented Span-based Network (STSN), a span-based joint model that can make use of token-level label information. In STSN, we construct a core neural architecture by deep stacking multiple attention layers, each of which consists of three basic attention units. On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE. Experimental results on three benchmark datasets show that STSN consistently outperforms the strongest baselines in terms of F1, creating new state-of-the-art results.

cs.CL↗

arXiv2022

A Two-Phase Paradigm for Joint Entity-Relation Extraction

An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction task. However, these models sample a large number of negative entities and negative relations during the model training, which are essential but result in grossly imbalanced data distributions and in turn cause suboptimal model performance. In order to address the above issues, we propose a two-phase paradigm for the span-based joint entity and relation extraction, which involves classifying the entities and relations in the first phase, and predicting the types of these entities and relations in the second phase. The two-phase paradigm enables our model to significantly reduce the data distribution gap, including the gap between negative entities and other entities, as well as the gap between negative relations and other relations. In addition, we make the first attempt at combining entity type and entity distance as global features, which has proven effective, especially for the relation extraction. Experimental results on several datasets demonstrate that the spanbased joint extraction model augmented with the two-phase paradigm and the global features consistently outperforms previous state-of-the-art span-based models for the joint extraction task, establishing a new standard benchmark. Qualitative and quantitative analyses further validate the effectiveness the proposed paradigm and the global features.

cs.CL↗

arXiv2022

Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes

Few-shot named entity recognition (NER) enables us to build a NER system for a new domain using very few labeled examples. However, existing prototypical networks for this task suffer from roughly estimated label dependency and closely distributed prototypes, thus often causing misclassifications. To address the above issues, we propose EP-Net, an Entity-level Prototypical Network enhanced by dispersedly distributed prototypes. EP-Net builds entity-level prototypes and considers text spans to be candidate entities, so it no longer requires the label dependency. In addition, EP-Net trains the prototypes from scratch to distribute them dispersedly and aligns spans to prototypes in the embedding space using a space projection. Experimental results on two evaluation tasks and the Few-NERD settings demonstrate that EP-Net consistently outperforms the previous strong models in terms of overall performance. Extensive analyses further validate the effectiveness of EP-Net.

cs.CL↗

arXiv2022

A Context-Aware Approach for Textual Adversarial Attack through Probability Difference Guided Beam Search

Textual adversarial attacks expose the vulnerabilities of text classifiers and can be used to improve their robustness. Existing context-aware methods solely consider the gold label probability and use the greedy search when searching an attack path, often limiting the attack efficiency. To tackle these issues, we propose PDBS, a context-aware textual adversarial attack model using Probability Difference guided Beam Search. The probability difference is an overall consideration of all class label probabilities, and PDBS uses it to guide the selection of attack paths. In addition, PDBS uses the beam search to find a successful attack path, thus avoiding suffering from limited search space. Extensive experiments and human evaluation demonstrate that PDBS outperforms previous best models in a series of evaluation metrics, especially bringing up to a +19.5% attack success rate. Ablation studies and qualitative analyses further confirm the efficiency of PDBS.

cs.CL↗

arXiv2022

Boosting Span-based Joint Entity and Relation Extraction via Squence Tagging Mechanism

Span-based joint extraction simultaneously conducts named entity recognition (NER) and relation extraction (RE) in text span form. Recent studies have shown that token labels can convey crucial task-specific information and enrich token semantics. However, as far as we know, due to completely abstain from sequence tagging mechanism, all prior span-based work fails to use token label in-formation. To solve this problem, we pro-pose Sequence Tagging enhanced Span-based Network (STSN), a span-based joint extrac-tion network that is enhanced by token BIO label information derived from sequence tag-ging based NER. By stacking multiple atten-tion layers in depth, we design a deep neu-ral architecture to build STSN, and each atten-tion layer consists of three basic attention units. The deep neural architecture first learns seman-tic representations for token labels and span-based joint extraction, and then constructs in-formation interactions between them, which also realizes bidirectional information interac-tions between span-based NER and RE. Fur-thermore, we extend the BIO tagging scheme to make STSN can extract overlapping en-tity. Experiments on three benchmark datasets show that our model consistently outperforms previous optimal models by a large margin, creating new state-of-the-art results.

cs.CL↗

arXiv2022

Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition

For Named Entity Recognition (NER), sequence labeling-based and span-based paradigms are quite different. Previous research has demonstrated that the two paradigms have clear complementary advantages, but few models have attempted to leverage these advantages in a single NER model as far as we know. In our previous work, we proposed a paradigm known as Bundling Learning (BL) to address the above problem. The BL paradigm bundles the two NER paradigms, enabling NER models to jointly tune their parameters by weighted summing each paradigm's training loss. However, three critical issues remain unresolved: When does BL work? Why does BL work? Can BL enhance the existing state-of-the-art (SOTA) NER models? To address the first two issues, we implement three NER models, involving a sequence labeling-based model--SeqNER, a span-based NER model--SpanNER, and BL-NER that bundles SeqNER and SpanNER together. We draw two conclusions regarding the two issues based on the experimental results on eleven NER datasets from five domains. We then apply BL to five existing SOTA NER models to investigate the third issue, consisting of three sequence labeling-based models and two span-based models. Experimental results indicate that BL consistently enhances their performance, suggesting that it is possible to construct a new SOTA NER system by incorporating BL into the current SOTA system. Moreover, we find that BL reduces both entity boundary and type prediction errors. In addition, we compare two commonly used labeling tagging methods as well as three types of span semantic representations.

cs.CL↗

arXiv2022

Topic-Grained Text Representation-based Model for Document Retrieval

Document retrieval enables users to find their required documents accurately and quickly. To satisfy the requirement of retrieval efficiency, prevalent deep neural methods adopt a representation-based matching paradigm, which saves online matching time by pre-storing document representations offline. However, the above paradigm consumes vast local storage space, especially when storing the document as word-grained representations. To tackle this, we present TGTR, a Topic-Grained Text Representation-based Model for document retrieval. Following the representation-based matching paradigm, TGTR stores the document representations offline to ensure retrieval efficiency, whereas it significantly reduces the storage requirements by using novel topicgrained representations rather than traditional word-grained. Experimental results demonstrate that compared to word-grained baselines, TGTR is consistently competitive with them on TREC CAR and MS MARCO in terms of retrieval accuracy, but it requires less than 1/10 of the storage space required by them. Moreover, TGTR overwhelmingly surpasses global-grained baselines in terms of retrieval accuracy.

cs.IR↗

arXiv2022

SummScore: A Comprehensive Evaluation Metric for Summary Quality Based on Cross-Encoder

Text summarization models are often trained to produce summaries that meet human quality requirements. However, the existing evaluation metrics for summary text are only rough proxies for summary quality, suffering from low correlation with human scoring and inhibition of summary diversity. To solve these problems, we propose SummScore, a comprehensive metric for summary quality evaluation based on CrossEncoder. Firstly, by adopting the original-summary measurement mode and comparing the semantics of the original text, SummScore gets rid of the inhibition of summary diversity. With the help of the text-matching pre-training Cross-Encoder, SummScore can effectively capture the subtle differences between the semantics of summaries. Secondly, to improve the comprehensiveness and interpretability, SummScore consists of four fine-grained submodels, which measure Coherence, Consistency, Fluency, and Relevance separately. We use semi-supervised multi-rounds of training to improve the performance of our model on extremely limited annotated data. Extensive experiments show that SummScore significantly outperforms existing evaluation metrics in the above four dimensions in correlation with human scoring. We also provide the quality evaluation results of SummScore on 16 mainstream summarization models for later research.

cs.CL↗

arXiv2022

Astroconformer: Inferring Surface Gravity of Stars from Stellar Light Curves with Transformer

We introduce Astroconformer, a Transformer-based model to analyze stellar light curves from the Kepler mission. We demonstrate that Astrconformer can robustly infer the stellar surface gravity as a supervised task. Importantly, as Transformer captures long-range information in the time series, it outperforms the state-of-the-art data-driven method in the field, and the critical role of self-attention is proved through ablation experiments. Furthermore, the attention map from Astroconformer exemplifies the long-range correlation information learned by the model, leading to a more interpretable deep learning approach for asteroseismology. Besides data from Kepler, we also show that the method can generalize to sparse cadence light curves from the Rubin Observatory, paving the way for the new era of asteroseismology, harnessing information from long-cadence ground-based observations.

astro-ph.SR↗