arXiv subjects

Yang Xu

Publications and source records attributed to Yang Xu.

At least 343 records · Page 19Linked to original sources

arXiv2022

LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding

Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents. We propose LayoutLMv2 architecture with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. Specifically, with a two-stream multi-modal Transformer encoder, LayoutLMv2 uses not only the existing masked visual-language modeling task but also the new text-image alignment and text-image matching tasks, which make it better capture the cross-modality interaction in the pre-training stage. Meanwhile, it also integrates a spatial-aware self-attention mechanism into the Transformer architecture so that the model can fully understand the relative positional relationship among different text blocks. Experiment results show that LayoutLMv2 outperforms LayoutLM by a large margin and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including FUNSD (0.7895 $\to$ 0.8420), CORD (0.9493 $\to$ 0.9601), SROIE (0.9524 $\to$ 0.9781), Kleister-NDA (0.8340 $\to$ 0.8520), RVL-CDIP (0.9443 $\to$ 0.9564), and DocVQA (0.7295 $\to$ 0.8672). We made our model and code publicly available at \url{https://aka.ms/layoutlmv2}.

cs.CL↗

arXiv2021

Nonlinear Intensity Underwater Sonar Image Matching Method Based on Phase Information and Deep Convolution Features

In the field of deep-sea exploration, sonar is presently the only efficient long-distance sensing device. The complicated underwater environment, such as noise interference, low target intensity or background dynamics, has brought many negative effects on sonar imaging. Among them, the problem of nonlinear intensity is extremely prevalent. It is also known as the anisotropy of acoustic sensor imaging, that is, when autonomous underwater vehicles (AUVs) carry sonar to detect the same target from different angles, the intensity variation between image pairs is sometimes very large, which makes the traditional matching algorithm almost ineffective. However, image matching is the basis of comprehensive tasks such as navigation, positioning, and mapping. Therefore, it is very valuable to obtain robust and accurate matching results. This paper proposes a combined matching method based on phase information and deep convolution features. It has two outstanding advantages: one is that the deep convolution features could be used to measure the similarity of the local and global positions of the sonar image; the other is that local feature matching could be performed at the key target position of the sonar image. This method does not need complex manual designs, and completes the matching task of nonlinear intensity sonar images in a close end-to-end manner. Feature matching experiments are carried out on the deep-sea sonar images captured by AUVs, and the results show that our proposal has preeminent matching accuracy and robustness.

cs.CV↗

arXiv2021

Hierarchical Multi-robot Strategies Synthesis and Optimization under Individual and Collaborative Temporal Logic Specifications

This paper presents a hierarchical framework to solve the multi-robot temporal task planning problem. We assume that each robot has its individual task specification and the robots have to jointly satisfy a global collaborative task specification, both described in linear temporal logic. Specifically, a central server firstly extracts and decomposes a collaborative task sequence from the automaton corresponding to the collaborative task specification, and allocates the subtasks in the sequence to robots. The robots can then synthesize their initial execution strategies based on locally constructed product automatons, combining the assigned collaborative tasks and their individual task specifications. Furthermore, we propose a distributed execution strategy adjusting mechanism to iteratively improve the time efficiency, by reducing wait time in collaborations caused by potential synchronization constraints. We prove the completeness of the proposed framework under assumptions, and analyze its time complexity and optimality. Extensive simulation results verify the scalability and optimization efficiency of the proposed method.

cs.RO↗

arXiv2021

Inelastic Axial and Vector Structure Functions for Lepton-Nucleon Scattering 2021 Update

We report on an update (2021) of a phenomenological model for inelastic neutrino- and electron-nucleon scattering cross sections using effective leading order parton distribution functions with a new scaling variable $ξ_w$. Non-perturbative effects are well described using the $ξ_w$ scaling variable in combination with multiplicative $K$ factors at low $Q^2$. The model describes all inelastic charged-leptron-nucleon scattering data (HERA/NMC/BCDMS/SLAC/JLab) ranging from very high $Q^2$ to very low $Q^2$ and down to the $Q^2=0$ photo-production region. The model has been developed to be used in analysis of neutrino oscillation experiments in the few GeV region. The 2021 update accounts for the difference between axial and vector structure function which brings it into much better agreement with neutrino-nucleon total cross section measurements. The model has been developed primarily for hadronic final state masses $W$ above 1.8 GeV. However with additional parameters the model also describe the $average$ neutrino cross sections in the resonance region down to $W$=1.4 GeV.

hep-ph↗

arXiv2021

Breaking the curse of dimensionality with Isolation Kernel

The curse of dimensionality has been studied in different aspects. However, breaking the curse has been elusive. We show for the first time that it is possible to break the curse using the recently introduced Isolation Kernel. We show that only Isolation Kernel performs consistently well in indexed search, spectral & density peaks clustering, SVM classification and t-SNE visualization in both low and high dimensions, compared with distance, Gaussian and linear kernels. This is also supported by our theoretical analyses that Isolation Kernel is the only kernel that has the provable ability to break the curse, compared with existing metric-based Lipschitz continuous kernels.

cs.LG↗

arXiv2021

Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining

Natural language relies on a finite lexicon to express an unbounded set of emerging ideas. One result of this tension is the formation of new compositions, such that existing linguistic units can be combined with emerging items into novel expressions. We develop a framework that exploits the cognitive mechanisms of chaining and multimodal knowledge to predict emergent compositional expressions through time. We present the syntactic frame extension model (SFEM) that draws on the theory of chaining and knowledge from "percept", "concept", and "language" to infer how verbs extend their frames to form new compositions with existing and novel nouns. We evaluate SFEM rigorously on the 1) modalities of knowledge and 2) categorization models of chaining, in a syntactically parsed English corpus over the past 150 years. We show that multimodal SFEM predicts newly emerged verb syntax and arguments substantially better than competing models using purely linguistic or unimodal knowledge. We find support for an exemplar view of chaining as opposed to a prototype view and reveal how the joint approach of multimodal chaining may be fundamental to the creation of literal and figurative language uses including metaphor and metonymy.

cs.CL↗

arXiv2021

An unsupervised framework for tracing textual sources of moral change

Morality plays an important role in social well-being, but people's moral perception is not stable and changes over time. Recent advances in natural language processing have shown that text is an effective medium for informing moral change, but no attempt has been made to quantify the origins of these changes. We present a novel unsupervised framework for tracing textual sources of moral change toward entities through time. We characterize moral change with probabilistic topical distributions and infer the source text that exerts prominent influence on the moral time course. We evaluate our framework on a diverse set of data ranging from social media to news articles. We show that our framework not only captures fine-grained human moral judgments, but also identifies coherent source topics of moral change triggered by historical events. We apply our methodology to analyze the news in the COVID-19 pandemic and demonstrate its utility in identifying sources of moral change in high-impact and real-time social events.

cs.CL↗

arXiv2021

Evolution of emotion semantics

Humans possess the unique ability to communicate emotions through language. Although concepts like anger or awe are abstract, there is a shared consensus about what these English emotion words mean. This consensus may give the impression that their meaning is static, but we propose this is not the case. We cannot travel back to earlier periods to study emotion concepts directly, but we can examine text corpora, which have partially preserved the meaning of emotion words. Using natural language processing of historical text, we found evidence for semantic change in emotion words over the past century and that varying rates of change were predicted in part by an emotion concept's prototypicality - how representative it is of the broader category of "emotion". Prototypicality negatively correlated with historical rates of emotion semantic change obtained from text-based word embeddings, beyond more established variables including usage frequency in English and a second comparison language, French. This effect for prototypicality did not consistently extend to the semantic category of birds, suggesting its relevance for predicting semantic change may be category-dependent. Our results suggest emotion semantics are evolving over time, with prototypical emotion words remaining semantically stable, while other emotion words evolve more freely.

cs.CL↗

arXiv2021

A Galois Connection Approach to Wei-Type Duality Theorems

In $1991$, Wei proved a duality theorem that established an interesting connection between the generalized Hamming weights of a linear code and those of its dual code. Wei's duality theorem has since been extensively studied from different perspectives and extended to other settings. In this paper, we re-examine Wei's duality theorem and its various extensions, henceforth referred to as Wei-type duality theorems, from a new Galois connection perspective. Our approach is based on the observation that the generalized Hamming weights and the dimension/length profiles of a linear code form a Galois connection. The central result in this paper is a general Wei-type duality theorem for two Galois connections between finite subsets of $\mathbb{Z}$, from which all the known Wei-type duality theorems can be recovered. As corollaries of our central result, we prove new Wei-type duality theorems for $w$-demimatroids defined over finite sets and $w$-demi-polymatroids defined over modules with a composition series, which further allows us to unify and generalize all the known Wei-type duality theorems established for codes endowed with various metrics.

cs.IT↗

arXiv2021

Fourier-Reflexive Partitions Induced by Poset Metric

Let $\mathbf{H}$ be the cartesian product of a family of finite abelian groups indexed by a finite set $Ω$. A given poset (i.e., partially ordered set) $\mathbf{P}=(Ω,\preccurlyeq_{\mathbf{P}})$ gives rise to a poset metric on $\mathbf{H}$, which further leads to a partition $\mathcal{Q}(\mathbf{H},\mathbf{P})$ of $\mathbf{H}$. We prove that if $\mathcal{Q}(\mathbf{H},\mathbf{P})$ is Fourier-reflexive, then its dual partition $Λ$ coincides with the partition of $\hat{\mathbf{H}}$ induced by $\mathbf{\overline{P}}$, the dual poset of $\mathbf{P}$, and moreover, $\mathbf{P}$ is necessarily hierarchical. This result establishes a conjecture proposed by Gluesing-Luerssen in \cite{4}. We also show that with some other assumptions, $Λ$ is finer than the partition of $\hat{\mathbf{H}}$ induced by $\mathbf{\overline{P}}$. In addition, we give some necessary and sufficient conditions for $\mathbf{P}$ to be hierarchical, and for the case that $\mathbf{P}$ is hierarchical, we give an explicit criterion for determining whether two codewords in $\hat{\mathbf{H}}$ belong to the same block of $Λ$. We prove these results by relating the involved partitions with certain family of polynomials, a generalized version of which is also proposed and studied to generalize the aforementioned results.

cs.IT↗

arXiv2021

What do writing features tell us about AI papers?

As the numbers of submissions to conferences grow quickly, the task of assessing the quality of academic papers automatically, convincingly, and with high accuracy attracts increasing attention. We argue that studying interpretable dimensions of these submissions could lead to scalable solutions. We extract a collection of writing features, and construct a suite of prediction tasks to assess the usefulness of these features in predicting citation counts and the publication of AI-related papers. Depending on the venues, the writing features can predict the conference vs. workshop appearance with F1 scores up to 60-90, sometimes even outperforming the content-based tf-idf features and RoBERTa. We show that the features describe writing style more than content. To further understand the results, we estimate the causal impact of the most indicative features. Our analysis on writing features provides a perspective to assessing and refining the writing of academic articles at scale.

cs.CL↗

arXiv2021

Measuring Financial Time Series Similarity With a View to Identifying Profitable Stock Market Opportunities

Forecasting stock returns is a challenging problem due to the highly stochastic nature of the market and the vast array of factors and events that can influence trading volume and prices. Nevertheless it has proven to be an attractive target for machine learning research because of the potential for even modest levels of prediction accuracy to deliver significant benefits. In this paper, we describe a case-based reasoning approach to predicting stock market returns using only historical pricing data. We argue that one of the impediments for case-based stock prediction has been the lack of a suitable similarity metric when it comes to identifying similar pricing histories as the basis for a future prediction -- traditional Euclidean and correlation based approaches are not effective for a variety of reasons -- and in this regard, a key contribution of this work is the development of a novel similarity metric for comparing historical pricing data. We demonstrate the benefits of this metric and the case-based approach in a real-world application in comparison to a variety of conventional benchmarks.

q-fin.ST↗

arXiv2021

SIMPL: Generating Synthetic Overhead Imagery to Address Zero-shot and Few-Shot Detection Problems

Recently deep neural networks (DNNs) have achieved tremendous success for object detection in overhead (e.g., satellite) imagery. One ongoing challenge however is the acquisition of training data, due to high costs of obtaining satellite imagery and annotating objects in it. In this work we present a simple approach - termed Synthetic object IMPLantation (SIMPL) - to easily and rapidly generate large quantities of synthetic overhead training data for custom target objects. We demonstrate the effectiveness of using SIMPL synthetic imagery for training DNNs in zero-shot scenarios where no real imagery is available; and few-shot learning scenarios, where limited real-world imagery is available. We also conduct experiments to study the sensitivity of SIMPL's effectiveness to some key design parameters, providing users for insights when designing synthetic imagery for custom objects. We release a software implementation of our SIMPL approach so that others can build upon it, or use it for their own custom problems.

cs.CV↗

arXiv2021

A diachronic evaluation of gender asymmetry in euphemism

The use of euphemisms is a known driver of language change. It has been proposed that women use euphemisms more than men. Although there have been several studies investigating gender differences in language, the claim about euphemism usage has not been tested comprehensively through time. If women do use euphemisms more, this could mean that women also lead the formation of new euphemisms and language change over time. Using four large diachronic text corpora of English, we evaluate the claim that women use euphemisms more than men through a quantitative analysis. We assembled a list of 106 euphemism-taboo pairs to analyze their relative use through time by each gender in the corpora. Contrary to the existing belief, our results show that women do not use euphemisms with a higher proportion than men. We repeated the analysis using different subsets of the euphemism-taboo pairs list and found that our result was robust. Our study indicates that in a broad range of settings involving both speech and writing, and with varying degrees of formality, women do not use or form euphemisms more than men.

cs.CL↗

arXiv2021

MultiXNet: Multiclass Multistage Multimodal Motion Prediction

One of the critical pieces of the self-driving puzzle is understanding the surroundings of a self-driving vehicle (SDV) and predicting how these surroundings will change in the near future. To address this task we propose MultiXNet, an end-to-end approach for detection and motion prediction based directly on lidar sensor data. This approach builds on prior work by handling multiple classes of traffic actors, adding a jointly trained second-stage trajectory refinement step, and producing a multimodal probability distribution over future actor motion that includes both multiple discrete traffic behaviors and calibrated continuous position uncertainties. The method was evaluated on large-scale, real-world data collected by a fleet of SDVs in several cities, with the results indicating that it outperforms existing state-of-the-art approaches.

cs.CV↗

arXiv2021

A Computational Framework for Slang Generation

Slang is a common type of informal language, but its flexible nature and paucity of data resources present challenges for existing natural language systems. We take an initial step toward machine generation of slang by developing a framework that models the speaker's word choice in slang context. Our framework encodes novel slang meaning by relating the conventional and slang senses of a word while incorporating syntactic and contextual knowledge in slang usage. We construct the framework using a combination of probabilistic inference and neural contrastive learning. We perform rigorous evaluations on three slang dictionaries and show that our approach not only outperforms state-of-the-art language models, but also better predicts the historical emergence of slang word usages from 1960s to 2000s. We interpret the proposed models and find that the contrastively learned semantic space is sensitive to the similarities between slang and conventional senses of words. Our work creates opportunities for the automated generation and interpretation of informal language.

cs.CL↗

arXiv2021

How is BERT surprised? Layerwise detection of linguistic anomalies

Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly. In this work, we use Gaussian models for density estimation at intermediate layers of three language models (BERT, RoBERTa, and XLNet), and evaluate our method on BLiMP, a grammaticality judgement benchmark. In lower layers, surprisal is highly correlated to low token frequency, but this correlation diminishes in upper layers. Next, we gather datasets of morphosyntactic, semantic, and commonsense anomalies from psycholinguistic studies; we find that the best performing model RoBERTa exhibits surprisal in earlier layers when the anomaly is morphosyntactic than when it is semantic, while commonsense anomalies do not exhibit surprisal at any intermediate layer. These results suggest that language models employ separate mechanisms to detect different types of linguistic anomalies.

cs.CL↗

arXiv2021

Integration of Unpaired Single-cell Chromatin Accessibility and Gene Expression Data via Adversarial Learning

Deep learning has empowered analysis for single-cell sequencing data in many ways and has generated deep understanding about a range of complex cellular systems. As the booming single-cell sequencing technologies brings the surge of high dimensional data that come from different sources and represent cellular systems with different features, there is an equivalent rise and challenge of integrating single-cell sequence across modalities. Here, we present a novel adversarial approach to integrate single-cell chromatin accessibility and gene expression data in a semi-supervised manner. We demonstrate that our method substantially improves data integration from a simple adversarial domain adaption approach, and it also outperforms two state-of-the-art (SOTA) methods.

q-bio.GN↗