arXiv subjects

Yue Zhang

Publications and source records attributed to Yue Zhang.

At least 649 records · Page 36Linked to original sources

arXiv2021

On Compositional Generalization of Neural Machine Translation

Modern neural machine translation (NMT) models have achieved competitive performance in standard benchmarks such as WMT. However, there still exist significant issues such as robustness, domain generalization, etc. In this paper, we study NMT models from the perspective of compositional generalization by building a benchmark dataset, CoGnition, consisting of 216k clean and consistent sentence pairs. We quantitatively analyze effects of various factors using compound translation error rate, then demonstrate that the NMT model fails badly on compositional generalization, although it performs remarkably well under traditional metrics.

cs.CL↗

arXiv2021

V2V Spatiotemporal Interactive Pattern Recognition and Risk Analysis in Lane Changes

In complex lane change (LC) scenarios, semantic interpretation and safety analysis of dynamic interactive pattern are necessary for autonomous vehicles to make appropriate decisions. This study proposes an unsupervised learning framework that combines primitive-based interactive pattern recognition methods and risk analysis methods. The Hidden Markov Model with the Gaussian mixture model (GMM-HMM) approach is developed to decompose the LC scenarios into primitives. Then the Dynamic Time Warping (DTW) distance based K-means clustering is applied to gather the primitives to 13 types of interactive patterns. Finally, this study considers two types of time-to-collision (TTC) involved in the LC process as indicators to analyze the risk of the interactive patterns and extract high-risk LC interactive patterns. The results obtained from The Highway Drone Dataset (highD) demonstrate that the identified LC interactive patterns contain interpretable semantic information. This study explores the spatiotemporal evolution law and risk formation mechanism of the LC interactive patterns and the findings are useful for comprehensively understanding the latent interactive patterns, improving the rationality and safety of autonomous vehicle's decision-making.

eess.SP↗

arXiv2021

Towards Navigation by Reasoning over Spatial Configurations

We deal with the navigation problem where the agent follows natural language instructions while observing the environment. Focusing on language understanding, we show the importance of spatial semantics in grounding navigation instructions into visual perceptions. We propose a neural agent that uses the elements of spatial configurations and investigate their influence on the navigation agent's reasoning ability. Moreover, we model the sequential execution order and align visual objects with spatial configurations in the instruction. Our neural agent improves strong baselines on the seen environments and shows competitive performance on the unseen environments. Additionally, the experimental results demonstrate that explicit modeling of spatial semantic elements in the instructions can improve the grounding and spatial reasoning of the model.

cs.CL↗

arXiv2021

Sufficient conditions for compactness of the $\overline{\partial}$-Neumann operator on high level forms

By establishing a unified estimate of the twisted Kohn-Morrey-Hörmander estimate and the $q$-pseudoconvex Ahn-Zampieri estimate, we discuss variants of Property $(P_q)$ of Catlin and Property $(\widetilde{P_q})$ of McNeal on the boundary of a smooth pseudoconvex domain in $\mathbb{C}^n$ for certain high level forms. These variant conditions on the one side, imply $L^2$-compactness of the $\overline{\partial}$-Neumann operator on the associated domain, on the other side, are different from the classical Property $(P_q)$ and Property $(\widetilde{P_q})$. As an application of our result, we show that if the Hausdorff $(2n-2)$-dimensional measure of the weakly pseudoconvex points on the boundary of a smooth bounded pseudoconvex domain is zero, then the $\overline{\partial}$-Neumann operator $N_{n-1}$ is $L^2$-compact on $(0,n-1)$-level forms. This result generalizes Boas and Sibony's results on $(0,1)$-level forms.

math.CV↗

arXiv2021

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing

Various robustness evaluation methodologies from different perspectives have been proposed for different natural language processing (NLP) tasks. These methods have often focused on either universal or task-specific generalization capabilities. In this work, we propose a multilingual robustness evaluation platform for NLP tasks (TextFlint) that incorporates universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis. TextFlint enables practitioners to automatically evaluate their models from all aspects or to customize their evaluations as desired with just a few lines of code. To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one. TextFlint generates complete analytical reports as well as targeted augmented data to address the shortcomings of the model's robustness. To validate TextFlint's utility, we performed large-scale empirical evaluations (over 67,000 evaluations) on state-of-the-art deep learning models, classic supervised methods, and real-world systems. Almost all models showed significant performance degradation, including a decline of more than 50% of BERT's prediction accuracy on tasks such as aspect-level sentiment classification, named entity recognition, and natural language inference. Therefore, we call for the robustness to be included in the model evaluation, so as to promote the healthy development of NLP technology.

cs.CL↗

arXiv2021

Higgs Portal From The Atmosphere To Hyper-K

A light Higgs portal scalar could be abundantly produced in the earth's atmosphere and decay in large-volume neutrino detectors. We point out that the Hyper-Kamiokande detector bears a strong discovery potential of probing such particles in an uncharted parameter space that is actively explored by intensity frontier experiments including rare kaon decays. The signal we propose to look for is electron-positron pair creation that manifests as a double-ring appearing from the same vertex. Most of these pairs originate from zenith angles above the Hyper-K detector's horizon. This search can be generalized to other new light states and is highly complementary to beam experiments.

hep-ph↗

arXiv2021

Contextualized Rewriting for Text Summarization

Extractive summarization suffers from irrelevance, redundancy and incoherence. Existing work shows that abstractive rewriting for extractive summaries can improve the conciseness and readability. These rewriting systems consider extracted summaries as the only input, which is relatively focused but can lose important background knowledge. In this paper, we investigate contextualized rewriting, which ingests the entire original document. We formalize contextualized rewriting as a seq2seq problem with group alignments, introducing group tag as a solution to model the alignments, identifying extracted summaries through content-based addressing. Results show that our approach significantly outperforms non-contextualized rewriting systems without requiring reinforcement learning, achieving strong improvements on ROUGE scores upon multiple extractive summarizers.

cs.CL↗

arXiv2021

CleanML: A Study for Evaluating the Impact of Data Cleaning on ML Classification Tasks

Data quality affects machine learning (ML) model performances, and data scientists spend considerable amount of time on data cleaning before model training. However, to date, there does not exist a rigorous study on how exactly cleaning affects ML -- ML community usually focuses on developing ML algorithms that are robust to some particular noise types of certain distributions, while database (DB) community has been mostly studying the problem of data cleaning alone without considering how data is consumed by downstream ML analytics. We propose a CleanML study that systematically investigates the impact of data cleaning on ML classification tasks. The open-source and extensible CleanML study currently includes 14 real-world datasets with real errors, five common error types, seven different ML models, and multiple cleaning algorithms for each error type (including both commonly used algorithms in practice as well as state-of-the-art solutions in academic literature). We control the randomness in ML experiments using statistical hypothesis testing, and we also control false discovery rate in our experiments using the Benjamini-Yekutieli (BY) procedure. We analyze the results in a systematic way to derive many interesting and nontrivial observations. We also put forward multiple research directions for researchers.

cs.DB↗

arXiv2021

Constrained Text Generation with Global Guidance -- Case Study on CommonGen

This paper studies constrained text generation, which is to generate sentences under certain pre-conditions. We focus on CommonGen, the task of generating text based on a set of concepts, as a representative task of constrained text generation. Traditional methods mainly rely on supervised training to maximize the likelihood of target sentences.However, global constraints such as common sense and coverage cannot be incorporated into the likelihood objective of the autoregressive decoding process. In this paper, we consider using reinforcement learning to address the limitation, measuring global constraints including fluency, common sense and concept coverage with a comprehensive score, which serves as the reward for reinforcement learning. Besides, we design a guided decoding method at the word, fragment and sentence levels. Experiments demonstrate that our method significantly increases the concept coverage and outperforms existing models in various automatic evaluations.

cs.CL↗

arXiv2021

PA-ResSeg: A Phase Attention Residual Network for Liver Tumor Segmentation from Multi-phase CT Images

In this paper, we propose a phase attention residual network (PA-ResSeg) to model multi-phase features for accurate liver tumor segmentation, in which a phase attention (PA) is newly proposed to additionally exploit the images of arterial (ART) phase to facilitate the segmentation of portal venous (PV) phase. The PA block consists of an intra-phase attention (Intra-PA) module and an inter-phase attention (Inter-PA) module to capture channel-wise self-dependencies and cross-phase interdependencies, respectively. Thus it enables the network to learn more representative multi-phase features by refining the PV features according to the channel dependencies and recalibrating the ART features based on the learned interdependencies between phases. We propose a PA-based multi-scale fusion (MSF) architecture to embed the PA blocks in the network at multiple levels along the encoding path to fuse multi-scale features from multi-phase images. Moreover, a 3D boundary-enhanced loss (BE-loss) is proposed for training to make the network more sensitive to boundaries. To evaluate the performance of our proposed PA-ResSeg, we conducted experiments on a multi-phase CT dataset of focal liver lesions (MPCT-FLLs). Experimental results show the effectiveness of the proposed method by achieving a dice per case (DPC) of 0.77.87, a dice global (DG) of 0.8682, a volumetric overlap error (VOE) of 0.3328 and a relative volume difference (RVD) of 0.0443 on the MPCT-FLLs. Furthermore, to validate the effectiveness and robustness of PA-ResSeg, we conducted extra experiments on another multi-phase liver tumor dataset and obtained a DPC of 0.8290, a DG of 0.9132, a VOE of 0.2637 and a RVD of 0.0163. The proposed method shows its robustness and generalization capability in different datasets and different backbones.

eess.IV↗

arXiv2021

Structural Information Preserving for Graph-to-Text Generation

The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs. As a crucial defect, the current state-of-the-art models may mess up or even drop the core structural information of input graphs when generating outputs. We propose to tackle this problem by leveraging richer training signals that can guide our model for preserving input information. In particular, we introduce two types of autoencoding losses, each individually focusing on different aspects (a.k.a. views) of input graphs. The losses are then back-propagated to better calibrate our model via multi-task training. Experiments on two benchmarks for graph-to-text generation show the effectiveness of our approach over a state-of-the-art baseline. Our code is available at \url{http://github.com/Soistesimmer/AMR-multiview}.

cs.CL↗

arXiv2021

Evaluating Commonsense in Pre-trained Language Models

Contextualized representations trained over large raw text data have given remarkable improvements for NLP tasks including question answering and reading comprehension. There have been works showing that syntactic, semantic and word sense knowledge are contained in such representations, which explains why they benefit such tasks. However, relatively little work has been done investigating commonsense knowledge contained in contextualized representations, which is crucial for human question answering and reading comprehension. We study the commonsense ability of GPT, BERT, XLNet, and RoBERTa by testing them on seven challenging benchmarks, finding that language modeling and its variants are effective objectives for promoting models' commonsense ability while bi-directional context and larger training set are bonuses. We additionally find that current models do poorly on tasks require more necessary inference steps. Finally, we test the robustness of models by making dual test cases, which are correlated so that the correct prediction of one sample should lead to correct prediction of the other. Interestingly, the models show confusion on these test cases, which suggests that they learn commonsense at the surface rather than the deep level. We release a test set, named CATs publicly, for future research.

cs.CL↗

arXiv2021

Origin of Sterile Neutrino Dark Matter via Vector Secret Neutrino Interactions

Secret neutrino interactions can play an essential role in the origin of dark matter. We present an anatomy of production mechanisms for sterile neutrino dark matter, a keV-scale gauge-singlet fermion that mixes with active neutrinos, in the presence of a new vector boson mediating secret interactions among active neutrinos. We identify three regimes of the vector boson's mass and coupling where it makes distinct impact on dark matter production through the dispersion relations and/or scattering rates. We also analyze models with gauged $L_μ-L_τ$ and $B-L$ numbers which have a similar dark matter cosmology but different vector boson phenomenology. We derive the parameter space in these models where the observed relic abundance is produced for sterile neutrino dark matter. They serve as well-motivated target for the upcoming experimental searches.

hep-ph↗

arXiv2021

Field-free spin-orbit torque-induced switching of perpendicular magnetization in a ferrimagnetic layer with vertical composition gradient

Current-induced spin-orbit torques (SOTs) are of interest for fast and energy-efficient manipulation of magnetic order in spintronic devices. To be deterministic, however, switching of perpendicularly magnetized materials by SOT requires a mechanism for in-plane symmetry breaking. Existing methods to do so involve the application of an in-plane bias magnetic field, or incorporation of in-plane structural asymmetry in the device, both of which can be difficult to implement in practical applications. Here, we reported bias-field-free SOT switching in a single perpendicular CoTb layer with an engineered vertical composition gradient. The vertical structural inversion asymmetry induces strong intrinsic SOTs and a gradient-driven Dzyaloshinskii-Moriya interaction (g-DMI), which breaks the in-plane symmetry during the switching process. Micromagnetic simulations are in agreement with experimental results, and elucidate the role of g-DMI in the deterministic switching. This bias-field-free switching scheme for perpendicular ferrimagnets with g-DMI provides a strategy for efficient and compact SOT device design.

cond-mat.mes-hall↗

arXiv2020

Estimating The Effect Of Subscription based Streaming Services On The Demand For Game Consoles

In this paper, we attempt to estimate the effect of the implementation of subscription-based streaming services on the demand of the associated game consoles. We do this by applying the BLP demand estimation model proposed by Berry (1994). This results in a linear demand specification which can be identified using conventional identification methods such as instrumental variables estimation and fixed-effects models. We find that given our dataset, the two-stage least squares (2SLS) regression provides us with convincing estimates that subscription-based streaming services does have a positive effect on the demand of game consoles as proposed by the general principle of complementary goods.

econ.GN↗

arXiv2020

Investigating Typed Syntactic Dependencies for Targeted Sentiment Classification Using Graph Attention Neural Network

Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts. Dominant methods employ neural networks for encoding the input sentence and extracting relations between target mentions and their contexts. Recently, graph neural network has been investigated for integrating dependency syntax for the task, achieving the state-of-the-art results. However, existing methods do not consider dependency label information, which can be intuitively useful. To solve the problem, we investigate a novel relational graph attention network that integrates typed syntactic dependency information. Results on standard benchmarks show that our method can effectively leverage label information for improving targeted sentiment classification performances. Our final model significantly outperforms state-of-the-art syntax-based approaches.

cs.CL↗

arXiv2020

End-to-End Chinese Parsing Exploiting Lexicons

Chinese parsing has traditionally been solved by three pipeline systems including word-segmentation, part-of-speech tagging and dependency parsing modules. In this paper, we propose an end-to-end Chinese parsing model based on character inputs which jointly learns to output word segmentation, part-of-speech tags and dependency structures. In particular, our parsing model relies on word-char graph attention networks, which can enrich the character inputs with external word knowledge. Experiments on three Chinese parsing benchmark datasets show the effectiveness of our models, achieving the state-of-the-art results on end-to-end Chinese parsing.

cs.CL↗

arXiv2020

Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts

Natural language inference (NLI) is a fundamental NLP task, investigating the entailment relationship between two texts. Popular NLI datasets present the task at sentence-level. While adequate for testing semantic representations, they fall short for testing contextual reasoning over long texts, which is a natural part of the human inference process. We introduce ConTRoL, a new dataset for ConTextual Reasoning over Long texts. Consisting of 8,325 expert-designed "context-hypothesis" pairs with gold labels, ConTRoL is a passage-level NLI dataset with a focus on complex contextual reasoning types such as logical reasoning. It is derived from competitive selection and recruitment test (verbal reasoning test) for police recruitment, with expert level quality. Compared with previous NLI benchmarks, the materials in ConTRoL are much more challenging, involving a range of reasoning types. Empirical results show that state-of-the-art language models perform by far worse than educated humans. Our dataset can also serve as a testing-set for downstream tasks like Checking Factual Correctness of Summaries.

cs.CL↗