arXiv subjects

Fei Li

Publications and source records attributed to Fei Li.

At least 109 records · Page 6Linked to original sources

arXiv2024

Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing

Structured Sentiment Analysis (SSA) was cast as a problem of bi-lexical dependency graph parsing by prior studies. Multiple formulations have been proposed to construct the graph, which share several intrinsic drawbacks: (1) The internal structures of spans are neglected, thus only the boundary tokens of spans are used for relation prediction and span recognition, thus hindering the model's expressiveness; (2) Long spans occupy a significant proportion in the SSA datasets, which further exacerbates the problem of internal structure neglect. In this paper, we treat the SSA task as a dependency parsing task on partially-observed dependency trees, regarding flat spans without determined tree annotations as latent subtrees to consider internal structures of spans. We propose a two-stage parsing method and leverage TreeCRFs with a novel constrained inside algorithm to model latent structures explicitly, which also takes advantages of joint scoring graph arcs and headed spans for global optimization and inference. Results of extensive experiments on five benchmark datasets reveal that our method performs significantly better than all previous bi-lexical methods, achieving new state-of-the-art.

cs.CL↗

arXiv2024

Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information

Existing cross-document event coreference resolution models, which either compute mention similarity directly or enhance mention representation by extracting event arguments (such as location, time, agent, and patient), lacking the ability to utilize document-level information. As a result, they struggle to capture long-distance dependencies. This shortcoming leads to their underwhelming performance in determining coreference for the events where their argument information relies on long-distance dependencies. In light of these limitations, we propose the construction of document-level Rhetorical Structure Theory (RST) trees and cross-document Lexical Chains to model the structural and semantic information of documents. Subsequently, cross-document heterogeneous graphs are constructed and GAT is utilized to learn the representations of events. Finally, a pair scorer calculates the similarity between each pair of events and co-referred events can be recognized using standard clustering algorithm. Additionally, as the existing cross-document event coreference datasets are limited to English, we have developed a large-scale Chinese cross-document event coreference dataset to fill this gap, which comprises 53,066 event mentions and 4,476 clusters. After applying our model on the English and Chinese datasets respectively, it outperforms all baselines by large margins.

cs.CL↗

arXiv2024

Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm

Document-level event extraction aims to extract structured event information from unstructured text. However, a single document often contains limited event information and the roles of different event arguments may be biased due to the influence of the information source. This paper addresses the limitations of traditional document-level event extraction by proposing the task of cross-document event extraction (CDEE) to integrate event information from multiple documents and provide a comprehensive perspective on events. We construct a novel cross-document event extraction dataset, namely CLES, which contains 20,059 documents and 37,688 mention-level events, where over 70% of them are cross-document. To build a benchmark, we propose a CDEE pipeline that includes 5 steps, namely event extraction, coreference resolution, entity normalization, role normalization and entity-role resolution. Our CDEE pipeline achieves about 72% F1 in end-to-end cross-document event extraction, suggesting the challenge of this task. Our work builds a new line of information extraction research and will attract new research attention.

cs.CL↗

arXiv2024

RMFA-Net: A Neural ISP for Real RAW to RGB Image Reconstruction

Deep learning-based ISP algorithms have demonstrated significant potential in raw2rgb reconstruction. However, existing networks have not fully considered the specific characteristics of raw data, such as black level and CFA, which can negatively impact texture and color if mishandled. Moreover, uneven exposure in raw data is also not considered carefully, leading to adverse effects on contrast and brightness. In this paper, we introduce RMFA-Net to tackle these problems. We perform implicit black level correction to mitigate color shifts in dim scenes. To preserve high-frequency information and prevent misalignment, we propose a novel Three-Channel-Split mode. To address the issue of uneven exposure, we designed an explicit tone mapping module based on the Retinex theory. We train and evaluate our models using the dataset released by the Mobile AI 2022 Learned Smartphone ISP Challenge. It is demonstrated that RMFA-Net outperforms previous algorithms, achieving a PSNR score of over 25 dB, surpassing the state-of-the-art by +1 dB. Furthermore, we developed a lightweight version, RMFANet-tiny, for engineering deployment while still maintaining strong performance, surpassing the SOTA by +0.5 dB.

eess.IV↗

arXiv2024

Recognizing Everything from All Modalities at Once: Grounded Multimodal Universal Information Extraction

In the field of information extraction (IE), tasks across a wide range of modalities and their combinations have been traditionally studied in isolation, leaving a gap in deeply recognizing and analyzing cross-modal information. To address this, this work for the first time introduces the concept of grounded Multimodal Universal Information Extraction (MUIE), providing a unified task framework to analyze any IE tasks over various modalities, along with their fine-grained groundings. To tackle MUIE, we tailor a multimodal large language model (MLLM), Reamo, capable of extracting and grounding information from all modalities, i.e., recognizing everything from all modalities at once. Reamo is updated via varied tuning strategies, equipping it with powerful capabilities for information recognition and fine-grained multimodal grounding. To address the absence of a suitable benchmark for grounded MUIE, we curate a high-quality, diverse, and challenging test set, which encompasses IE tasks across 9 common modality combinations with the corresponding multimodal groundings. The extensive comparison of Reamo with existing MLLMs integrated into pipeline approaches demonstrates its advantages across all evaluation dimensions, establishing a strong benchmark for the follow-up research. Our resources are publicly released at https://haofei.vip/MUIE.

cs.MM↗

arXiv2024

A fully plasma based electron injector for a linear collider or XFEL

We demonstrate through high-fidelity particle-in-cell simulations a simple approach for efficiently generating 20+ GeV electron beams with the necessary charge, energy spread, and emittance for use as the injector for an electron arm of a future linear collider or a next generation XFEL. The self-focusing of an unmatched, relatively low quality, drive beam results in self-injection by elongating the wakefield excited in the nonlinear blowout regime. Over pump depletion distances, the drive beam dynamics and self-loading from the injected beam leads to extremely high quality and high energy output beams. For plasma densities of $10^{18} \ \text{cm}^{-3}$, PIC simulation results indicate that self-injected beams with $0.52 \ \text{nC}$ of charge can be accelerated to $\sim 20$ GeV energies with projected energy spreads, $\lesssim 1\%$ within the beam core, slice normalized emittances as low as $110 \ \text{nm}$, a peak normalized brightness $\gtrsim 10^{19} \ \text{A}/\text{m}^2/\text{rad}^2$, and energy transfer efficiencies $\gtrsim 54\%$.

physics.acc-ph↗

arXiv2024

Production of light nuclei in isobaric Ru+Ru and Zr+Zr collisions at $\sqrt{s_{\mathrm{NN}}}$ =7.7-200 GeV from a multiphase transport model

The production of light nuclei in isobaric $^{96}_{44}$Ru + $^{96}_{44}$Ru and $^{96}_{40}$Zr + $^{96}_{40}$Zr collisions, ranging from $\sqrt{s_{NN}}$ = 7.7 to 200 GeV, are studied using the string melting version of A Multi Phase Transport (AMPT) model in combination with a coalescence approach to light nuclei production. From the calculated yields, transverse momentum $p_{T}$ spectra, and rapidity dependences of light nuclei $p$, $n$, $d$, $t$, ${}^{3}$He, we find that the Ru+Ru/Zr+Zr ratios for the yields of these particles exceed unity with the inclusion of a quadrupole deformation $β_{ 2 }$ and octupole deformation $β_{ 3 }$ as well as the neutron skins. We also find that heavier particles have a larger deviation from unity. Furthermore, we find that as the collision energy increases, the influence of isospin effects on the production of light nuclei in isobar collisions gradually decreases, while the influence of nuclear structure becomes more significant, particularly evident from the energy dependence of the deuteron ratio, which is unaffected by isospin effects.

nucl-th↗

arXiv2024

Correlations between X-rays, Visible Light and Drive-Beam Energy Loss Observed in Plasma Wakefield Acceleration Experiments at FACET-II

This study documents several correlations observed during the first run of the plasma wakefield acceleration experiment E300 conducted at FACET-II, using a single drive electron bunch. The established correlations include those between the measured maximum energy loss of the drive electron beam and the integrated betatron x-ray signal, the calculated total beam energy deposited in the plasma and the integrated x-ray signal, among three visible light emission measuring cameras, and between the visible plasma light and x-ray signal. The integrated x-ray signal correlates almost linearly with both the maximum energy loss of the drive beam and the energy deposited into the plasma, demonstrating its usability as a measure of energy transfer from the drive beam to the plasma. Visible plasma light is found to be a useful indicator of the presence of wake at three locations that overall are two meters apart. Despite the complex dynamics and vastly different timescales, the x-ray radiation from the drive bunch and visible light emission from the plasma may prove to be effective non-invasive diagnostics for monitoring the energy transfer from the beam to the plasma in future high-repetition-rate experiments.

physics.plasm-ph↗

arXiv2024

Ultrafast Electron Diffraction with MeV Electron Source from a Laser Wakefield Accelerator

MeV ultrafast electron diffraction (UED) is a widely used technology for ultrafast structural dynamic studies of matters in numerous areas. The development of laser wakefield accelerator (LWFA) envisions great potential of advanced all-optical electron source based on LWFA in UED applications. We experimentally demonstrated that an LWFA-based device with a miniaturized permanent magnet beamline can generate and manipulate electron beams suitable for UED. In the beam transmission, the LWFA electron beams with intrinsic short duration stretch due to energy spread and then are compressed by a following double bend achromat. The optimized double bend achromat can make the beamline isochronous such that the arrival time jitter induced by the shot-to-shot energy fluctuation can be eliminated, and allow the advantage of the natural laser-beam synchronization for LWFAs to emerge. With the energy filtering, the beam energy spread can be reduced to 3% (FWHM) while a sufficient amount of charge (11.9 fC) per bunch for diffraction is retained. Start-to-end simulations showed that the bunch length reaches ~30 fs (rms) with the same experimental configuration. Clear single-shot and multi-shot diffraction patterns of single-crystalline gold samples are obtained and the derived lattice constant agrees excellently with the real value. Our proof-of-principle experiments open the door to the detection of ultrafast structural dynamics using MeV LWFA beams, and pave the way for the UED applications with sub-10-fs temporal resolution.

physics.acc-ph↗

arXiv2024

Modeling Unified Semantic Discourse Structure for High-quality Headline Generation

Headline generation aims to summarize a long document with a short, catchy title that reflects the main idea. This requires accurately capturing the core document semantics, which is challenging due to the lengthy and background information-rich na ture of the texts. In this work, We propose using a unified semantic discourse structure (S3) to represent document semantics, achieved by combining document-level rhetorical structure theory (RST) trees with sentence-level abstract meaning representation (AMR) graphs to construct S3 graphs. The hierarchical composition of sentence, clause, and word intrinsically characterizes the semantic meaning of the overall document. We then develop a headline generation framework, in which the S3 graphs are encoded as contextual features. To consolidate the efficacy of S3 graphs, we further devise a hierarchical structure pruning mechanism to dynamically screen the redundant and nonessential nodes within the graph. Experimental results on two headline generation datasets demonstrate that our method outperforms existing state-of-art methods consistently. Our work can be instructive for a broad range of document modeling tasks, more than headline or summarization generation.

cs.CL↗

arXiv2024

Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server

In federated learning, data heterogeneity significantly impacts performance. A typical solution involves segregating these parameters into shared and personalized components, a concept also relevant in multi-task learning. Addressing this, we propose "Loop Improvement" (LI), a novel method enhancing this separation and feature extraction without necessitating a central server or data interchange among participants. Our experiments reveal LI's superiority in several aspects: In personalized federated learning environments, LI consistently outperforms the advanced FedALA algorithm in accuracy across diverse scenarios. Additionally, LI's feature extractor closely matches the performance achieved when aggregating data from all clients. In global model contexts, employing LI with stacked personalized layers and an additional network also yields comparable results to combined client data scenarios. Furthermore, LI's adaptability extends to multi-task learning, streamlining the extraction of common features across tasks and obviating the need for simultaneous training. This approach not only enhances individual task performance but also achieves accuracy levels on par with classic multi-task learning methods where all tasks are trained simultaneously. LI integrates a loop topology with layer-wise and end-to-end training, compatible with various neural network models. This paper also delves into the theoretical underpinnings of LI's effectiveness, offering insights into its potential applications. The code is on https://github.com/axedge1983/LI

cs.LG↗

arXiv2024

Unification of spatiotemporal quantum formalisms: mapping between process and pseudo-density matrices via multiple-time states

We consider the relation between three different approaches to defining quantum states across several times and locations: the pseudo-density matrix (PDM), the process matrix, and the multiple-time state approaches. Previous studies have shown that bipartite two-time states can reproduce the statistics of bipartite process matrices. Here, we show that the operational scenarios underlying two-time states can be represented as PDMs, and thereby construct a mapping from process matrices with measurements to PDMs. The existence of this mapping implies that PDMs can, like the process matrix, model processes with indefinite causal orders. The results contribute to the unification of quantum models of spatiotemporal states.

quant-ph↗

arXiv2024

CMNER: A Chinese Multimodal NER Dataset based on Social Media

Multimodal Named Entity Recognition (MNER) is a pivotal task designed to extract named entities from text with the support of pertinent images. Nonetheless, a notable paucity of data for Chinese MNER has considerably impeded the progress of this natural language processing task within the Chinese domain. Consequently, in this study, we compile a Chinese Multimodal NER dataset (CMNER) utilizing data sourced from Weibo, China's largest social media platform. Our dataset encompasses 5,000 Weibo posts paired with 18,326 corresponding images. The entities are classified into four distinct categories: person, location, organization, and miscellaneous. We perform baseline experiments on CMNER, and the outcomes underscore the effectiveness of incorporating images for NER. Furthermore, we conduct cross-lingual experiments on the publicly available English MNER dataset (Twitter2015), and the results substantiate our hypothesis that Chinese and English multimodal NER data can mutually enhance the performance of the NER model.

cs.CL↗

arXiv2024

Imagining density distribution of molecular orbitals in IR+XUV co-rotating circular laser fields by frequency-domain theory

We have investigated the angle-resolved ATI spectrum of oriented molecules in the IR+XUV co-rotating circular laser fields. According to the different roles of IR and XUV laser in the ionization process, we purposefully adjust the photon energy of XUV and the intensity of IR laser to make the ionization spectrum of the molecule distributed in a suitable momentum region. Moreover, under the same laser conditions, the background fringes in the ionization spectrum of the molecule can be removed by using the ionization spectrum of the atom with the same ionization energy as the molecule, so that the molecular orbital density distribution in the suitable momentum region can be obtained. That is, for any unknown molecule, as long as the ionization energy of the molecule can be measured, the density distribution of the molecular orbital can be imaged in a definite momentum region by adjusting the laser field conditions, which may shed light on the experimental detection of molecular orbitals.

physics.atom-ph↗

arXiv2024

Observations of high-order multiplicity in a high-mass stellar protocluster

The dominant mechanism forming multiple stellar systems in the high-mass regime (M$_\ast \gtrsim $ 8 $M_{\odot}$) remained unknown because direct imaging of multiple protostellar systems at early phases of high-mass star formation is very challenging. High-mass stars are expected to form in clustered environments containing binaries and higher-order multiplicity systems. So far only a few high-mass protobinary systems, and no definitive higher-order multiples, have been detected. Here we report the discovery of one quintuple, one quadruple, one triple and four binary protostellar systems simultaneously forming in a single high-mass protocluster, G333.23--0.06, using Atacama Large Millimeter/submillimeter Array high-resolution observations. We present a new example of a group of gravitationally bound binary and higher-order multiples during their early formation phases in a protocluster. This provides the clearest direct measurement of the initial configuration of primordial high-order multiple systems, with implications for the in situ multiplicity and its origin. We find that the binary and higher-order multiple systems, and their parent cores, show no obvious sign of disk-like kinematic structure. We conclude that the observed fragmentation into binary and higher-order multiple systems can be explained by core fragmentation, indicating its crucial role in establishing the multiplicity during high-mass star cluster formation.

astro-ph.GA↗

arXiv2023

Gas-phase molecules in protoplanetary nebulae with the 21 μm emission feature

It has been more than 30 years since the enigmatic 21 μm emission feature was first discovered in protoplanetary nebulae (PPNs). Although dozens of different dust carrier candidates have been proposed, there is as yet no widely accepted one. We present the results of molecular observations toward 21μm objects using the 10m Submillimeter Telescope of Arizona Radio Observatory at the 1.3 mm band and the 13.7 m telescope of Purple Mountain Observatory at the 3mm band, aiming to investigate whether the gas-phase environments of these unusual sources have some peculiarities compared to normal PPNs. We detect 31 emission lines belonging to seven different molecular species, most of which are the first detection in 21 μm PPNs. The observations provide clues on the identification of the 21 μm feature. We report a correlation study between the fractional abundance of gas-phase molecules and the strengths of the 21 μm emission. Our study shows that given the small sample size, the 21 μm feature has weak or no correlations with the gas-phase molecules. Future radio observations of high spatial and spectral resolution toward a large sample are desirable to elucidate the 21 μm emission phenomena.

astro-ph.GA↗

arXiv2023

Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought

With the proliferation of dialogic data across the Internet, the Dialogue Commonsense Multi-choice Question Answering (DC-MCQ) task has emerged as a response to the challenge of comprehending user queries and intentions. Although prevailing methodologies exhibit effectiveness in addressing single-choice questions, they encounter difficulties in handling multi-choice queries due to the heightened intricacy and informational density. In this paper, inspired by the human cognitive process of progressively excluding options, we propose a three-step Reverse Exclusion Graph-of-Thought (ReX-GoT) framework, including Option Exclusion, Error Analysis, and Combine Information. Specifically, our ReX-GoT mimics human reasoning by gradually excluding irrelevant options and learning the reasons for option errors to choose the optimal path of the GoT and ultimately infer the correct answer. By progressively integrating intricate clues, our method effectively reduces the difficulty of multi-choice reasoning and provides a novel solution for DC-MCQ. Extensive experiments on the CICERO and CICERO$_{v2}$ datasets validate the significant improvement of our approach on DC-MCQ task. On zero-shot setting, our model outperform the best baseline by 17.67% in terms of F1 score for the multi-choice task. Most strikingly, our GPT3.5-based ReX-GoT framework achieves a remarkable 39.44% increase in F1 score.

cs.CL↗

arXiv2023

Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approach

Despite significant advancements in multi-label text classification, the ability of existing models to generalize to novel and seldom-encountered complex concepts, which are compositions of elementary ones, remains underexplored. This research addresses this gap. By creating unique data splits across three benchmarks, we assess the compositional generalization ability of existing multi-label text classification models. Our results show that these models often fail to generalize to compositional concepts encountered infrequently during training, leading to inferior performance on tests with these new combinations. To address this, we introduce a data augmentation method that leverages two innovative text generation models designed to enhance the classification models' capacity for compositional generalization. Our experiments show that this data augmentation approach significantly improves the compositional generalization capabilities of classification models on our benchmarks, with both generation models surpassing other text generation baselines.

cs.CL↗