arXiv subjects

Junjie Hu

Publications and source records attributed to Junjie Hu.

At least 127 records · Page 7Linked to original sources

arXiv2022

MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages

We present the results of the Workshop on Multilingual Information Access (MIA) 2022 Shared Task, evaluating cross-lingual open-retrieval question answering (QA) systems in 16 typologically diverse languages. In this task, we adapted two large-scale cross-lingual open-retrieval QA datasets in 14 typologically diverse languages, and newly annotated open-retrieval QA data in 2 underrepresented languages: Tagalog and Tamil. Four teams submitted their systems. The best system leveraging iteratively mined diverse negative examples and larger pretrained models achieves 32.2 F1, outperforming our baseline by 4.5 points. The second best system uses entity-aware contextualized representations for document retrieval, and achieves significant improvements in Tamil (20.8 F1), whereas most of the other systems yield nearly zero scores.

cs.CL↗

arXiv2022

Feature Pyramid Attention based Residual Neural Network for Environmental Sound Classification

Environmental sound classification (ESC) is a challenging problem due to the unstructured spatial-temporal relations that exist in the sound signals. Recently, many studies have focused on abstracting features from convolutional neural networks while the learning of semantically relevant frames of sound signals has been overlooked. To this end, we present an end-to-end framework, namely feature pyramid attention network (FPAM), focusing on abstracting the semantically relevant features for ESC. We first extract the feature maps of the preprocessed spectrogram of the sound waveform by a backbone network. Then, to build multi-scale hierarchical features of sound spectrograms, we construct a feature pyramid representation of the sound spectrograms by aggregating the feature maps from multi-scale layers, where the temporal frames and spatial locations of semantically relevant frames are localized by FPAM. Specifically, the multiple features are first processed by a dimension alignment module. Afterward, the pyramid spatial attention module (PSA) is attached to localize the important frequency regions spatially with a spatial attention module (SAM). Last, the processed feature maps are refined by a pyramid channel attention (PCA) to localize the important temporal frames. To justify the effectiveness of the proposed FPAM, visualization of attention maps on the spectrograms has been presented. The visualization results show that FPAM can focus more on the semantic relevant regions while neglecting the noises. The effectiveness of the proposed methods is validated on two widely used ESC datasets: the ESC-50 and ESC-10 datasets. The experimental results show that the FPAM yields comparable performance to state-of-the-art methods. A substantial performance increase has been achieved by FPAM compared with the baseline methods.

cs.SD↗

arXiv2022

GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems

Much recent progress in task-oriented dialogue (ToD) systems has been driven by available annotation data across multiple domains for training. Over the last few years, there has been a move towards data curation for multilingual ToD systems that are applicable to serve people speaking different languages. However, existing multilingual ToD datasets either have a limited coverage of languages due to the high cost of data curation, or ignore the fact that dialogue entities barely exist in countries speaking these languages. To tackle these limitations, we introduce a novel data curation method that generates GlobalWoZ -- a large-scale multilingual ToD dataset globalized from an English ToD dataset for three unexplored use cases. Our method is based on translating dialogue templates and filling them with local entities in the target-language countries. We release our dataset as well as a set of strong baselines to encourage research on learning multilingual ToD systems for real use cases.

cs.CL↗

arXiv2021

Risk of Bitcoin Market: Volatility, Jumps, and Forecasts

Cryptocurrency, the most controversial and simultaneously the most interesting asset, has attracted many investors and speculators in recent years. The visibly significant market capitalization of cryptos also motivates modern financial instruments such as futures and options. Those will depend on the dynamics, volatility, or even the jumps of cryptos. We provide a comprehensive investigation of the risk dynamics of the Bitcoin Market from a realized volatility perspective. The Bitcoin market is extremely risky in the sense of volatility, entangled jumps, and extensive consecutive jumps, which reflect the major incidents worldwide. Empirical study shows that the lagged realized variance increases the future realized variance, while the jumps, especially positive ones, significantly reduce future realized variance. The out-of-sample forecasting model reveals that, in terms of forecasting accuracy and utility gain, investors interested in the long-term realized variance benefit from explicitly modelling the jumps and signed estimators, which is unnecessary for the short-term realized variance forecast.

q-fin.RM↗

arXiv2021

DEEP: DEnoising Entity Pre-training for Neural Machine Translation

It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. Earlier named entity translation methods mainly focus on phonetic transliteration, which ignores the sentence context for translation and is limited in domain and language coverage. To address this limitation, we propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences. Besides, we investigate a multi-task learning strategy that finetunes a pre-trained neural machine translation model on both entity-augmented monolingual data and parallel data to further improve entity translation. Experimental results on three language pairs demonstrate that \method results in significant improvements over strong denoising auto-encoding baselines, with a gain of up to 1.3 BLEU and up to 9.2 entity accuracy points for English-Russian translation.

cs.CL↗

arXiv2021

Advanced Statistical Learning on Short Term Load Process Forecasting

Short Term Load Forecast (STLF) is necessary for effective scheduling, operation optimization trading, and decision-making for electricity consumers. Modern and efficient machine learning methods are recalled nowadays to manage complicated structural big datasets, which are characterized by having a nonlinear temporal dependence structure. We propose different statistical nonlinear models to manage these challenges of hard type datasets and forecast 15-min frequency electricity load up to 2-days ahead. We show that the Long-short Term Memory (LSTM) and the Gated Recurrent Unit (GRU) models applied to the production line of a chemical production facility outperform several other predictive models in terms of out-of-sample forecasting accuracy by the Diebold-Mariano (DM) test with several metrics. The predictive information is fundamental for the risk and production management of electricity consumers.

stat.AP↗

arXiv2021

FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation

The RGB-Thermal (RGB-T) information for semantic segmentation has been extensively explored in recent years. However, most existing RGB-T semantic segmentation usually compromises spatial resolution to achieve real-time inference speed, which leads to poor performance. To better extract detail spatial information, we propose a two-stage Feature-Enhanced Attention Network (FEANet) for the RGB-T semantic segmentation task. Specifically, we introduce a Feature-Enhanced Attention Module (FEAM) to excavate and enhance multi-level features from both the channel and spatial views. Benefited from the proposed FEAM module, our FEANet can preserve the spatial information and shift more attention to high-resolution features from the fused RGB-T images. Extensive experiments on the urban scene dataset demonstrate that our FEANet outperforms other state-of-the-art (SOTA) RGB-T methods in terms of objective metrics and subjective visual comparison (+2.6% in global mAcc and +0.8% in global mIoU). For the 480 x 640 RGB-T test images, our FEANet can run with a real-time speed on an NVIDIA GeForce RTX 2080 Ti card.

cs.CV↗

arXiv2021

Networks of News and Cross-Sectional Returns

We uncover networks from news articles to study cross-sectional stock returns. By analyzing a huge dataset of more than 1 million news articles collected from the internet, we construct time-varying directed networks of the S&P500 stocks. The well-defined directed news networks are formed based on a modest assumption about firm-specific news structure, and we propose an algorithm to tackle type-I errors in identifying the stock tickers. We find strong evidence for the comovement effect between the news-linked stocks returns and reversal effect from the lead stock return on the 1-day ahead follower stock return, after controlling for many known effects. Furthermore, a series of portfolio tests reveal that the news network attention proxy, network degree, provides a robust and significant cross-sectional predictability of the monthly stock returns. Among different types of news linkages, the linkages of within-sector stocks, large size lead firms, and lead firms with lower stock liquidity are crucial for cross-sectional predictability.

q-fin.PM↗

arXiv2021

PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation

Unsupervised learning of depth from indoor monocular videos is challenging as the artificial environment contains many textureless regions. Fortunately, the indoor scenes are full of specific structures, such as planes and lines, which should help guide unsupervised depth learning. This paper proposes PLNet that leverages the plane and line priors to enhance the depth estimation. We first represent the scene geometry using local planar coefficients and impose the smoothness constraint on the representation. Moreover, we enforce the planar and linear consistency by randomly selecting some sets of points that are probably coplanar or collinear to construct simple and effective consistency losses. To verify the proposed method's effectiveness, we further propose to evaluate the flatness and straightness of the predicted point cloud on the reliable planar and linear regions. The regularity of these regions indicates quality indoor reconstruction. Experiments on NYU Depth V2 and ScanNet show that PLNet outperforms existing methods. The code is available at \url{https://github.com/HalleyJiang/PLNet}.

cs.CV↗

arXiv2021

XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation

Machine learning has brought striking advances in multilingual natural language processing capabilities over the past year. For example, the latest techniques have improved the state-of-the-art performance on the XTREME multilingual benchmark by more than 13 points. While a sizeable gap to human-level performance remains, improvements have been easier to achieve in some tasks than in others. This paper analyzes the current state of cross-lingual transfer learning and summarizes some lessons learned. In order to catalyze meaningful progress, we extend XTREME to XTREME-R, which consists of an improved set of ten natural language understanding tasks, including challenging language-agnostic retrieval tasks, and covers 50 typologically diverse languages. In addition, we provide a massively multilingual diagnostic suite (MultiCheckList) and fine-grained multi-dataset evaluation capabilities through an interactive public leaderboard to gain a better understanding of such models. The leaderboard and code for XTREME-R will be made available at https://sites.research.google/xtreme and https://github.com/google-research/xtreme respectively.

cs.CL↗

arXiv2021

Meta Reinforcement Learning Based Sensor Scanning in 3D Uncertain Environments for Heterogeneous Multi-Robot Systems

We study a novel problem that tackles learning based sensor scanning in 3D and uncertain environments with heterogeneous multi-robot systems. Our motivation is two-fold: first, 3D environments are complex, the use of heterogeneous multi-robot systems intuitively can facilitate sensor scanning by fully taking advantage of sensors with different capabilities. Second, in uncertain environments (e.g. rescue), time is of great significance. Since the learning process normally takes time to train and adapt to a new environment, we need to find an effective way to explore and adapt quickly. To this end, in this paper, we present a meta-learning approach to improve the exploration and adaptation capabilities. The experimental results demonstrate our method can outperform other methods by approximately 15%-27% on success rate and 70%-75% on adaptation speed.

cs.RO↗

arXiv2021

AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages

Reproducible benchmarks are crucial in driving progress of machine translation research. However, existing machine translation benchmarks have been mostly limited to high-resource or well-represented languages. Despite an increasing interest in low-resource machine translation, there are no standardized reproducible benchmarks for many African languages, many of which are used by millions of speakers but have less digitized textual data. To tackle these challenges, we propose AfroMT, a standardized, clean, and reproducible machine translation benchmark for eight widely spoken African languages. We also develop a suite of analysis tools for system diagnosis taking into account the unique properties of these languages. Furthermore, we explore the newly considered case of low-resource focused pretraining and develop two novel data augmentation-based strategies, leveraging word-level alignment information and pseudo-monolingual data for pretraining multilingual sequence-to-sequence models. We demonstrate significant improvements when pretraining on 11 languages, with gains of up to 2 BLEU points over strong baselines. We also show gains of up to 12 BLEU points over cross-lingual transfer baselines in data-constrained scenarios. All code and pretrained models will be released as further steps towards larger reproducible benchmarks for African languages.

cs.CL↗

arXiv2021

Phrase-level Active Learning for Neural Machine Translation

Neural machine translation (NMT) is sensitive to domain shift. In this paper, we address this problem in an active learning setting where we can spend a given budget on translating in-domain data, and gradually fine-tune a pre-trained out-of-domain NMT model on the newly translated data. Existing active learning methods for NMT usually select sentences based on uncertainty scores, but these methods require costly translation of full sentences even when only one or two key phrases within the sentence are informative. To address this limitation, we re-examine previous work from the phrase-based machine translation (PBMT) era that selected not full sentences, but rather individual phrases. However, while incorporating these phrases into PBMT systems was relatively simple, it is less trivial for NMT systems, which need to be trained on full sequences to capture larger structural properties of sentences unique to the new domain. To overcome these hurdles, we propose to select both full sentences and individual phrases from unlabelled data in the new domain for routing to human translators. In a German-English translation task, our active learning approach achieves consistent improvements over uncertainty-based sentence selection methods, improving up to 1.2 BLEU score over strong active learning baselines.

cs.CL↗

arXiv2021

Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models

This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings. Under a zero-shot setting, we empirically demonstrate that performance degrades significantly when we query the multilingual text-video model with non-English sentences. To address this problem, we introduce a multilingual multimodal pre-training strategy, and collect a new multilingual instructional video dataset (MultiHowTo100M) for pre-training. Experiments on VTT show that our method significantly improves video search in non-English languages without additional annotations. Furthermore, when multilingual annotations are available, our method outperforms recent baselines by a large margin in multilingual text-to-video search on VTT and VATEX; as well as in multilingual text-to-image search on Multi30K. Our model and Multi-HowTo100M is available at http://github.com/berniebear/Multi-HT100M.

cs.CV↗

arXiv2021

Explicit Alignment Objectives for Multilingual Bidirectional Encoders

Pre-trained cross-lingual encoders such as mBERT (Devlin et al., 2019) and XLMR (Conneau et al., 2020) have proven to be impressively effective at enabling transfer-learning of NLP systems from high-resource languages to low-resource languages. This success comes despite the fact that there is no explicit objective to align the contextual embeddings of words/sentences with similar meanings across languages together in the same space. In this paper, we present a new method for learning multilingual encoders, AMBER (Aligned Multilingual Bidirectional EncodeR). AMBER is trained on additional parallel data using two explicit alignment objectives that align the multilingual representations at different granularities. We conduct experiments on zero-shot cross-lingual transfer learning for different tasks including sequence tagging, sentence retrieval and sentence classification. Experimental results show that AMBER obtains gains of up to 1.1 average F1 score on sequence tagging and up to 27.3 average accuracy on retrieval over the XLMR-large model which has 3.2x the parameters of AMBER. Our code and models are available at http://github.com/junjiehu/amber.

cs.CL↗

arXiv2021

Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment

The core problem of visual multi-robot simultaneous localization and mapping (MR-SLAM) is how to efficiently and accurately perform multi-robot global localization (MR-GL). The difficulties are two-fold. The first is the difficulty of global localization for significant viewpoint difference. Appearance-based localization methods tend to fail under large viewpoint changes. Recently, semantic graphs have been utilized to overcome the viewpoint variation problem. However, the methods are highly time-consuming, especially in large-scale environments. This leads to the second difficulty, which is how to perform real-time global localization. In this paper, we propose a semantic histogram-based graph matching method that is robust to viewpoint variation and can achieve real-time global localization. Based on that, we develop a system that can accurately and efficiently perform MR-GL for both homogeneous and heterogeneous robots. The experimental results show that our approach is about 30 times faster than Random Walk based semantic descriptors. Moreover, it achieves an accuracy of 95% for global localization, while the accuracy of the state-of-the-art method is 85%.

cs.RO↗

arXiv2021

GEOMScope: Large Field-of-view 3D Lensless Microscopy with Low Computational Complexity

Recent development of lensless imagers has enabled three-dimensional (3D) imaging through a thin piece of optics in close proximity to a camera sensor. A general challenge of wide-field lensless imaging is the high computational complexity and slow speed to reconstruct 3D objects through iterative optimization process. Here, we demonstrated GEOMScope, a lensless 3D microscope that forms image through a single layer of microlens array and reconstructs objects through a geometrical-optics-based pixel back projection algorithm and background suppressions. Compared to others, our method allows local reconstruction, which significantly reduces the required computation resource and increases the reconstruction speed by orders of magnitude. This enables near real-time object reconstructions across a large volume of 23x23x5 mm^3, with a lateral resolution of 40 um and axial resolution of 300 um. Our system opens new avenues for broad biomedical applications such as endoscopy, which requires both miniaturized device footprint and real-time high resolution visualization.

physics.optics↗

arXiv2020

Curved boundary conditions of the lattice Boltzmann method for simulating microgaseous flows in the slip flow regime

The lattice Boltzmann method (LBM) has shown its promising capability in simulating microscale gas flows. However, the suitable boundary condition is still one of the critical issues for the LBM to model microgaseous flows involving curved geometries. In this paper, a local boundary condition of the LBM is proposed to treat curved solid walls of microgaseous flows. The developed boundary treatment combines the Maxwellian diffuse reflection scheme and a single-node boundary scheme which contains a free parameter as well as the distance ratio. The curved boundary condition is analyzed within the multiple-relaxation-time (MRT) model for a unidirectional microflow. It is shown that the derived slip velocity depends on the free parameter as well as the distance ratio and relaxation times. By virtue of the free parameter, the combination parameter and the uniform relaxation time are theoretically determined to realize the accurate slip boundary condition. In addition, it is found that besides the halfway diffuse-bounce-back (DBB) scheme, previous curved boundary schemes only containing the distance ratio cannot ensure uniform relaxation times to realize the slip boundary condition. Some numerical examples with planar and curved boundaries are carried out to validate the present curved boundary scheme. The good and robust consistency of numerical predictions with analytical solutions demonstrates our theoretical analysis.

physics.comp-ph↗