arXiv subjects

Juntao Li

Publications and source records attributed to Juntao Li.

At least 109 records · Page 6Linked to original sources

arXiv2023

CT4Rec: Simple yet Effective Consistency Training for Sequential Recommendation

Sequential recommendation methods are increasingly important in cutting-edge recommender systems. Through leveraging historical records, the systems can capture user interests and perform recommendations accordingly. State-of-the-art sequential recommendation models proposed very recently combine contrastive learning techniques for obtaining high-quality user representations. Though effective and performing well, the models based on contrastive learning require careful selection of data augmentation methods and pretext tasks, efficient negative sampling strategies, and massive hyper-parameters validation. In this paper, we propose an ultra-simple alternative for obtaining better user representations and improving sequential recommendation performance. Specifically, we present a simple yet effective \textbf{C}onsistency \textbf{T}raining method for sequential \textbf{Rec}ommendation (CT4Rec) in which only two extra training objectives are utilized without any structural modifications and data augmentation. Experiments on three benchmark datasets and one large newly crawled industrial corpus demonstrate that our proposed method outperforms SOTA models by a large margin and with much less training time than these based on contrastive learning. Online evaluation on real-world content recommendation system also achieves 2.717\% improvement on the click-through rate and 3.679\% increase on the average click number per capita. Further exploration reveals that such a simple method has great potential for CTR prediction. Our code is available at \url{https://github.com/ct4rec/CT4Rec.git}.

cs.IR↗

arXiv2023

A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond

Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and natural language processing communities. While NAR generation can significantly accelerate inference speed for machine translation, the speedup comes at the cost of sacrificed translation accuracy compared to its counterpart, autoregressive (AR) generation. In recent years, many new models and algorithms have been designed/proposed to bridge the accuracy gap between NAR generation and AR generation. In this paper, we conduct a systematic survey with comparisons and discussions of various non-autoregressive translation (NAT) models from different aspects. Specifically, we categorize the efforts of NAT into several groups, including data manipulation, modeling methods, training criterion, decoding algorithms, and the benefit from pre-trained models. Furthermore, we briefly review other applications of NAR models beyond machine translation, such as grammatical error correction, text summarization, text style transfer, dialogue, semantic parsing, automatic speech recognition, and so on. In addition, we also discuss potential directions for future exploration, including releasing the dependency of KD, reasonable training objectives, pre-training for NAR, and wider applications, etc. We hope this survey can help researchers capture the latest progress in NAR generation, inspire the design of advanced NAR models and algorithms, and enable industry practitioners to choose appropriate solutions for their applications. The web page of this survey is at \url{https://github.com/LitterBrother-Xiao/Overview-of-Non-autoregressive-Applications}.

cs.CL↗

arXiv2023

Can Diffusion Model Achieve Better Performance in Text Generation? Bridging the Gap between Training and Inference!

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward process during inference. Thus, the model only predicts based on the previously generated reverse noise rather than the noise computed by the forward process. Besides, the widely-used downsampling strategy in speeding up the inference will cause the mismatch of diffusion trajectories between training and inference. To understand and mitigate the above two types of training-inference discrepancies, we launch a thorough preliminary study. Based on our observations, we propose two simple yet effective methods to bridge the gaps mentioned above, named Distance Penalty and Adaptive Decay Sampling. Extensive experiments on \textbf{6} generation tasks confirm the superiority of our methods, which can achieve $100\times \rightarrow 200\times$ speedup with better performance.

cs.CL↗

arXiv2023

Test-Time Adaptation with Perturbation Consistency Learning

Currently, pre-trained language models (PLMs) do not cope well with the distribution shift problem, resulting in models trained on the training set failing in real test scenarios. To address this problem, the test-time adaptation (TTA) shows great potential, which updates model parameters to suit the test data at the testing time. Existing TTA methods rely on well-designed auxiliary tasks or self-training strategies based on pseudo-label. However, these methods do not achieve good trade-offs regarding performance gains and computational costs. To obtain some insights into such a dilemma, we take two representative TTA methods, i.e., Tent and OIL, for exploration and find that stable prediction is the key to achieving a good balance. Accordingly, in this paper, we propose perturbation consistency learning (PCL), a simple test-time adaptation method to promote the model to make stable predictions for samples with distribution shifts. Extensive experiments on adversarial robustness and cross-lingual transferring demonstrate that our method can achieve higher or comparable performance with less inference time over strong PLM backbones and previous state-of-the-art TTA methods.

cs.CL↗

arXiv2023

Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing

Currently, human-bot symbiosis dialog systems, e.g., pre- and after-sales in E-commerce, are ubiquitous, and the dialog routing component is essential to improve the overall efficiency, reduce human resource cost, and enhance user experience. Although most existing methods can fulfil this requirement, they can only model single-source dialog data and cannot effectively capture the underlying knowledge of relations among data and subtasks. In this paper, we investigate this important problem by thoroughly mining both the data-to-task and task-to-task knowledge among various kinds of dialog data. To achieve the above targets, we propose a Gated Mechanism enhanced Multi-task Model (G3M), specifically including a novel dialog encoder and two tailored gated mechanism modules. The proposed method can play the role of hierarchical information filtering and is non-invasive to existing dialog systems. Based on two datasets collected from real world applications, extensive experimental results demonstrate the effectiveness of our method, which achieves the state-of-the-art performance by improving 8.7\%/11.8\% on RMSE metric and 2.2\%/4.4\% on F1 metric.

cs.CL↗

arXiv2023

RenewNAT: Renewing Potential Translation for Non-Autoregressive Transformer

Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance. However, existing NAT models are difficult to achieve the desired efficiency-quality trade-off. For one thing, fully NAT models with efficient inference perform inferior to their autoregressive counterparts. For another, iterative NAT models can, though, achieve comparable performance while diminishing the advantage of speed. In this paper, we propose RenewNAT, a flexible framework with high efficiency and effectiveness, to incorporate the merits of fully and iterative NAT models. RenewNAT first generates the potential translation results and then renews them in a single pass. It can achieve significant performance improvements at the same expense as traditional NAT models (without introducing additional model parameters and decoding latency). Experimental results on various translation benchmarks (e.g., \textbf{4} WMT) show that our framework consistently improves the performance of strong fully NAT methods (e.g., GLAT and DSLP) without additional speed overhead.

cs.CL↗

arXiv2023

AMOM: Adaptive Masking over Masking for Conditional Masked Language Model

Transformer-based autoregressive (AR) methods have achieved appealing performance for varied sequence-to-sequence generation tasks, e.g., neural machine translation, summarization, and code generation, but suffer from low inference efficiency. To speed up the inference stage, many non-autoregressive (NAR) strategies have been proposed in the past few years. Among them, the conditional masked language model (CMLM) is one of the most versatile frameworks, as it can support many different sequence generation scenarios and achieve very competitive performance on these tasks. In this paper, we further introduce a simple yet effective adaptive masking over masking strategy to enhance the refinement capability of the decoder and make the encoder optimization easier. Experiments on \textbf{3} different tasks (neural machine translation, summarization, and code generation) with \textbf{15} datasets in total confirm that our proposed simple method achieves significant performance improvement over the strong CMLM model. Surprisingly, our proposed model yields state-of-the-art performance on neural machine translation (\textbf{34.62} BLEU on WMT16 EN$\to$RO, \textbf{34.82} BLEU on WMT16 RO$\to$EN, and \textbf{34.84} BLEU on IWSLT De$\to$En) and even better performance than the \textbf{AR} Transformer on \textbf{7} benchmark datasets with at least \textbf{2.2$\times$} speedup. Our code is available at GitHub.

cs.CL↗

arXiv2023

Solution Path Algorithm for Twin Multi-class Support Vector Machine

The twin support vector machine and its extensions have made great achievements in dealing with binary classification problems. However, it suffers from difficulties in effective solution of multi-classification and fast model selection. This work devotes to the fast regularization parameter tuning algorithm for the twin multi-class support vector machine. Specifically, a novel sample data set partition strategy is first adopted, which is the basis for the model construction. Then, combining the linear equations and block matrix theory, the Lagrangian multipliers are proved to be piecewise linear w.r.t. the regularization parameters, so that the regularization parameters are continuously updated by only solving the break points. Next, Lagrangian multipliers are proved to be 1 as the regularization parameter approaches infinity, thus, a simple yet effective initialization algorithm is devised. Finally, eight kinds of events are defined to seek for the starting event for the next iteration. Extensive experimental results on nine UCI data sets show that the proposed method can achieve comparable classification performance without solving any quadratic programming problem.

cs.LG↗

arXiv2023

Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study

A deployed question answering (QA) model can easily fail when the test data has a distribution shift compared to the training data. Robustness tuning (RT) methods have been widely studied to enhance model robustness against distribution shifts before model deployment. However, can we improve a model after deployment? To answer this question, we evaluate test-time adaptation (TTA) to improve a model after deployment. We first introduce COLDQA, a unified evaluation benchmark for robust QA against text corruption and changes in language and domain. We then evaluate previous TTA methods on COLDQA and compare them to RT methods. We also propose a novel TTA method called online imitation learning (OIL). Through extensive experiments, we find that TTA is comparable to RT methods, and applying TTA after RT can significantly boost the performance on COLDQA. Our proposed OIL improves TTA to be more robust to variation in hyper-parameters and test distributions over time.

cs.CL↗

arXiv2023

A room-temperature moiré interlayer exciton laser

Moiré superlattices in van der Waals heterostructures offer highly tunable quantum systems with emergent electronic and excitonic properties such as superconductivity, topological edge states, and moiré-trapped excitons. Theoretical calculations predicted the existence of the moiré potential at elevated temperatures; however, its impact on the optical properties of interlayer excitons (IXs) at room temperature is lacking, and the benefits of the moiré effects for lasing applications remain unexplored. We report that the moiré potential in a molybdenum disulfide/tungsten diselenide (MoS2/WSe2) heterobilayer system can significantly enhance light emission, elongate the IX lifetime, and modulate the IX emission energy at room temperature. By integrating a moiré superlattice with a silicon topological nanocavity, we achieve ultra-low-threshold lasing at the technologically important telecommunication O-band thanks to the significant moiré modulation. Moreover, the high-quality topological nanocavities facilitate the highest spectral coherence of < 0.1 nm linewidth among all reported two-dimensional material-based laser systems. Our findings not only open a new avenue for studying correlated states at elevated temperatures, but also enable novel architectures for integrated on-chip photonics and optoelectronics.

physics.optics↗

arXiv2022

Image-text Retrieval: A Survey on Recent Research and Development

In the past few years, cross-modal image-text retrieval (ITR) has experienced increased interest in the research community due to its excellent research value and broad real-world application. It is designed for the scenarios where the queries are from one modality and the retrieval galleries from another modality. This paper presents a comprehensive and up-to-date survey on the ITR approaches from four perspectives. By dissecting an ITR system into two processes: feature extraction and feature alignment, we summarize the recent advance of the ITR approaches from these two perspectives. On top of this, the efficiency-focused study on the ITR system is introduced as the third perspective. To keep pace with the times, we also provide a pioneering overview of the cross-modal pre-training ITR approaches as the fourth perspective. Finally, we outline the common benchmark datasets and valuation metric for ITR, and conduct the accuracy comparison among the representative ITR approaches. Some critical yet less studied issues are discussed at the end of the paper.

cs.IR↗

arXiv2022

Compound Super-oscillation Lens for Reflective Confocal Imaging

The super-oscillation lens (SOL) can achieve super-resolution focusing but have to trade-off with weaker hotspots and higher sidebands. We propose a single compound SOL to achieve reflective confocal imaging in principle without additional lenses. The designed SOL consists of an outer lens and an inner lens which play the role of focusing lens and collective lens respectively. As a result, focusing and collecting functions can be simultaneously realized. The improved system can achieve excellent imaging performance with an ultra-high resolution (<0.34λ/NA, NA stands for numerical aperture), and almost negligible side lobe ratio and no side bands, which proved superior to conventional laser scanning confocal microscopy and single SOL. This technology can be attractive for a variety of applications in super-resolution imaging and biomedical sciences.

physics.optics↗

arXiv2022

Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Change

Recent research has revealed that neural language models at scale suffer from poor temporal generalization capability, i.e., the language model pre-trained on static data from past years performs worse over time on emerging data. Existing methods mainly perform continual training to mitigate such a misalignment. While effective to some extent but is far from being addressed on both the language modeling and downstream tasks. In this paper, we empirically observe that temporal generalization is closely affiliated with lexical semantic change, which is one of the essential phenomena of natural languages. Based on this observation, we propose a simple yet effective lexical-level masking strategy to post-train a converged language model. Experiments on two pre-trained language models, two different classification tasks, and four benchmark datasets demonstrate the effectiveness of our proposed method over existing temporal adaptation methods, i.e., continual training with new data. Our code is available at \url{https://github.com/zhaochen0110/LMLM}.

cs.CL↗

arXiv2022

SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training

The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in real-world applications, label noise inevitably exists in training data, damaging the effectiveness, robustness, and generalization of the models constructed on such data. Recently, remarkable achievements have been made to mitigate this dilemma in visual data, while only a few explore textual data. To fill this gap, we present SelfMix, a simple yet effective method, to handle label noise in text classification tasks. SelfMix uses the Gaussian Mixture Model to separate samples and leverages semi-supervised learning. Unlike previous works requiring multiple models, our method utilizes the dropout mechanism on a single model to reduce the confirmation bias in self-training and introduces a textual-level mixup training strategy. Experimental results on three text classification benchmarks with different types of text show that the performance of our proposed method outperforms these strong baselines designed for both textual and visual data under different noise ratios and noise types. Our code is available at https://github.com/noise-learning/SelfMix.

cs.CL↗

arXiv2022

Chinese grammatical error correction based on knowledge distillation

In view of the poor robustness of existing Chinese grammatical error correction models on attack test sets and large model parameters, this paper uses the method of knowledge distillation to compress model parameters and improve the anti-attack ability of the model. In terms of data, the attack test set is constructed by integrating the disturbance into the standard evaluation data set, and the model robustness is evaluated by the attack test set. The experimental results show that the distilled small model can ensure the performance and improve the training speed under the condition of reducing the number of model parameters, and achieve the optimal effect on the attack test set, and the robustness is significantly improved. Code is available at https://github.com/Richard88888/KD-CGEC.

cs.CL↗

arXiv2022

Correction of aberrations via polarization in single layer metalenses

The correction of multiple aberrations in an optical system requires different optical elements, which increases its cost and complexity. Metasurfaces hold great promise to providing new functionality for miniaturized and low-cost optical systems. A key advantage over their bulk counterparts is the metasurface's ability to respond to the polarization of light, which adds a new degree of freedom to the optical design. Here, we show that polarization control enables a form-birefringent metalens to correct for both spherical and off-axis aberrations using a single element only, which is not possible with bulk optics. The metalens encodes two phase profiles onto the same surface, thus allowing switching from high resolution to wide field of view operation. Such ability to obtain both high resolution and wide field of view in a single layer is an important step towards integration of miniaturized optical systems, which may find many applications, e.g., in microscopy and endoscopy.

physics.optics↗

arXiv2022

Metalenses with polarization-independent adaptive nano-antennas

Metalens research has made major advances in recent years. These advances rely on the simple design principle of arranging meta-atoms in regular arrays to create an arbitrary phase and polarization profile. Unfortunately, the concept of equally spaced meta-atoms reaches its limit for high deflection angles where the deflection efficiency decreases. The efficiency can be increased using nano-antennas with multiple elements, but their polarization sensitivity hinders their application in metalenses. Here, we show that by designing polarization-insensitive dimer nano-antennas and abandoning the principle of equally spaced unit cells, polarization-independent ultrahigh numerical aperture (NA=1.48) oil-immersion operation with an efficiency of 43% can be demonstrated. This represents a significant improvement on other polarization-independent designs at visible wavelength. We also use this single layer metalens to replace a conventional objective lens and demonstrate the confocal scanning microscopic imaging of a grating with a period of 300 nm at 532 nm operating wavelength. Overall, our results experimentally demonstrate a novel design concept that further improves metalens performance.

physics.optics↗

arXiv2021

R-Drop: Regularized Dropout for Neural Networks

Dropout is a powerful and widely used technique to regularize the training of deep neural networks. In this paper, we introduce a simple regularization strategy upon dropout in model training, namely R-Drop, which forces the output distributions of different sub models generated by dropout to be consistent with each other. Specifically, for each training sample, R-Drop minimizes the bidirectional KL-divergence between the output distributions of two sub models sampled by dropout. Theoretical analysis reveals that R-Drop reduces the freedom of the model parameters and complements dropout. Experiments on $\bf{5}$ widely used deep learning tasks ($\bf{18}$ datasets in total), including neural machine translation, abstractive summarization, language understanding, language modeling, and image classification, show that R-Drop is universally effective. In particular, it yields substantial improvements when applied to fine-tune large-scale pre-trained models, e.g., ViT, RoBERTa-large, and BART, and achieves state-of-the-art (SOTA) performances with the vanilla Transformer model on WMT14 English$\to$German translation ($\bf{30.91}$ BLEU) and WMT14 English$\to$French translation ($\bf{43.95}$ BLEU), even surpassing models trained with extra large-scale data and expert-designed advanced variants of Transformer models. Our code is available at GitHub{\url{https://github.com/dropreg/R-Drop}}.

cs.LG↗