Showing 1–29 of 29 results for author: Zong, S

OnEvoMemory: Evolving Memory through Online Robot Rollouts for Pretrained Robot Policies

Authors: Zhongxi Chen, Shenqi Zong

Abstract: Long-horizon robot manipulation requires policies to track completed subtasks and critical interaction events. However, existing memory mechanisms heavily rely on external models or predefined update rules. To address this, we propose OnEvoMemory, a value-guided memory module for pretrained robot policies. It maintains recent context, high-value experiences, and salient transitions, while learning… ▽ More Long-horizon robot manipulation requires policies to track completed subtasks and critical interaction events. However, existing memory mechanisms heavily rely on external models or predefined update rules. To address this, we propose OnEvoMemory, a value-guided memory module for pretrained robot policies. It maintains recent context, high-value experiences, and salient transitions, while learning which experiences should be retained from trajectory outcomes. Offline demonstrations initialize the memory prior, whereas successful and unsuccessful online rollouts refine memory selection, helping the policy recognize task-stage transitions and avoid repeating completed subtasks. Experiments on long-horizon manipulation benchmarks show that OnEvoMemory improves the performance of the base VLA policy through both offline initialization and online memory evolution. △ Less

Submitted 9 August, 2026; originally announced August 2026.

Comments: 6 pages, 1 figure. Accepted as a poster at the ECCV 2026 Workshop on Embodied Multimodal Reasoning in Physical Environments (EMR)

Multi-Rate Mixture of Experts for Accelerating Liquid Neural Network Training

Authors: Shilong Zong, Almuatazbellah Boker, Hoda Eldardiry

Abstract: Multivariate time-series data often exhibit complex temporal dependencies, irregular sampling, and heterogeneous dynamics across multiple time scales, making accurate sequence modeling particularly challenging. Traditional recurrent neural networks (RNNs), such as Long Short-Term Memory (LSTM) networks, operate in discrete time and may struggle to effectively capture continuous and irregular tempo… ▽ More Multivariate time-series data often exhibit complex temporal dependencies, irregular sampling, and heterogeneous dynamics across multiple time scales, making accurate sequence modeling particularly challenging. Traditional recurrent neural networks (RNNs), such as Long Short-Term Memory (LSTM) networks, operate in discrete time and may struggle to effectively capture continuous and irregular temporal behaviors. Liquid Neural Networks (LNNs) address some of these limitations through continuous-time dynamics, but standard LNN architectures typically rely on a single dynamical system, limiting their ability to model heterogeneous temporal patterns. To address these challenges, we propose a Multi-Rate Mixture-of-Experts (MR-MoE) framework built on top of Liquid Neural Networks. In the proposed architecture, multiple LNN-based experts operate at distinct time scales, enabling the model to explicitly separate fast-changing dynamics from slow-evolving temporal trends. A gating network further enables adaptive expert specialization based on input conditions. In addition, we incorporate both feature-level and temporal attention mechanisms to improve robustness, interpretability, and long-range dependency modeling. Feature-level attention suppresses noisy or irrelevant variables, while temporal attention selectively focuses on informative historical states. We evaluate the proposed framework on a complex multivariate time-series prediction task and compare it against strong baselines, including LSTM, monolithic LNN, and standard MoE models. Experimental results demonstrate that the proposed MR-MoE framework consistently achieves improved AUROC and AUPRC performance while maintaining favorable computational efficiency. These results highlight the effectiveness of combining continuous-time dynamics, multi-scale expert decomposition, and adaptive attention mechanisms for time-series modeling. △ Less

Submitted 10 June, 2026; originally announced June 2026.

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Authors: PSBC LLM Team, Huawei LLM Team, Ruihan Long, Junjie Wu, Tianan Zhang, Duo Zhang, Yaozong Wu, Jinbin Fu, Chang Liu, Zhentao Tang, Wenshuang Yang, Xin Wang, Zhihao Song, Ning Huang, Wenjing Xu, Shuai Zong, Shupei Sun, Sen Wang, Jing Hu, Bin Wang, Xinyu Wang, Junkui Ju, Zequn Ding, Jie Ran, Man Luo , et al. (34 additional authors not shown)

Abstract: Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei… ▽ More Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69$\times$ increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43$\times$ concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference. △ Less

Submitted 4 June, 2026; originally announced June 2026.

Referenceless Proton Resonance Frequency Thermometry Using Deep Learning with Self-Attention

Authors: Yueran Zhao, Chang-Sheng Mei, Nathan J. McDannold, Shenyan Zong, Guofeng Shen

Abstract: Background: Accurate proton resonance frequency (PRF) MR thermometry is essential for monitoring temperature rise during thermal ablation with high intensity focused ultrasound (FUS). Conventional referenceless methods such as complex field estimation (CFE) and phase finite difference (PFD) tend to exhibit errors when susceptibility-induced phase discontinuities occur at tissue interfaces. Background: Accurate proton resonance frequency (PRF) MR thermometry is essential for monitoring temperature rise during thermal ablation with high intensity focused ultrasound (FUS). Conventional referenceless methods such as complex field estimation (CFE) and phase finite difference (PFD) tend to exhibit errors when susceptibility-induced phase discontinuities occur at tissue interfaces. △ Less

Submitted 27 November, 2025; originally announced December 2025.

Beyond Direct Generation: A Decomposed Approach to Well-Crafted Screenwriting with LLMs

Authors: Hang Lei, Shengyi Zong, Zhaoyan Li, Ziren Zhou, Hao Liu, Liang Yu

Abstract: The screenplay serves as the foundation for television production, defining narrative structure, character development, and dialogue. While Large Language Models (LLMs) show great potential in creative writing, direct end-to-end generation approaches often fail to produce well-crafted screenplays. We argue this failure stems from forcing a single model to simultaneously master two disparate capabi… ▽ More The screenplay serves as the foundation for television production, defining narrative structure, character development, and dialogue. While Large Language Models (LLMs) show great potential in creative writing, direct end-to-end generation approaches often fail to produce well-crafted screenplays. We argue this failure stems from forcing a single model to simultaneously master two disparate capabilities: creative narrative construction and rigid format adherence. The resulting outputs may mimic superficial style but lack the deep structural integrity and storytelling substance required for professional use. To enable LLMs to generate high-quality screenplays, we introduce Dual-Stage Refinement (DSR), a decomposed framework that decouples creative narrative generation from format conversion. The first stage transforms a brief outline into rich, novel-style prose. The second stage refines this narrative into a professionally formatted screenplay. This separation enables the model to specialize in one distinct capability at each stage. A key challenge in implementing DSR is the scarcity of paired outline-to-novel training data. We address this through hybrid data synthesis: reverse synthesis deconstructs existing screenplays into structured inputs, while forward synthesis leverages these inputs to generate high-quality narrative texts as training targets. Blind evaluations by professional screenwriters show that DSR achieves a 75% win rate against strong baselines like Gemini-2.5-Pro and reaches 82.7% of human-level performance. Our work demonstrates that decomposed generation architecture with tailored data synthesis effectively specializes LLMs in complex creative domains. △ Less

Submitted 7 January, 2026; v1 submitted 27 October, 2025; originally announced October 2025.

ACM Class: I.2.0

Accuracy, Memory Efficiency and Generalization: A Comparative Study on Liquid Neural Networks and Recurrent Neural Networks

Authors: Shilong Zong, Alex Bierly, Almuatazbellah Boker, Hoda Eldardiry

Abstract: This review aims to conduct a comparative analysis of liquid neural networks (LNNs) and traditional recurrent neural networks (RNNs) and their variants, such as long short-term memory networks (LSTMs) and gated recurrent units (GRUs). The core dimensions of the analysis include model accuracy, memory efficiency, and generalization ability. By systematically reviewing existing research, this paper… ▽ More This review aims to conduct a comparative analysis of liquid neural networks (LNNs) and traditional recurrent neural networks (RNNs) and their variants, such as long short-term memory networks (LSTMs) and gated recurrent units (GRUs). The core dimensions of the analysis include model accuracy, memory efficiency, and generalization ability. By systematically reviewing existing research, this paper explores the basic principles, mathematical models, key characteristics, and inherent challenges of these neural network architectures in processing sequential data. Research findings reveal that LNN, as an emerging, biologically inspired, continuous-time dynamic neural network, demonstrates significant potential in handling noisy, non-stationary data, and achieving out-of-distribution (OOD) generalization. Additionally, some LNN variants outperform traditional RNN in terms of parameter efficiency and computational speed. However, RNN remains a cornerstone in sequence modeling due to its mature ecosystem and successful applications across various tasks. This review identifies the commonalities and differences between LNNs and RNNs, summarizes their respective shortcomings and challenges, and points out valuable directions for future research, particularly emphasizing the importance of improving the scalability of LNNs to promote their application in broader and more complex scenarios. △ Less

Submitted 8 October, 2025; originally announced October 2025.

Comments: 13 pages, 12 figures. Submitted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

ACM Class: I.2.6; I.2.8

How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?

Authors: Xiliang Zhu, Shi Zong, David Rossouw

Abstract: Deploying Large Language Models (LLMs) for question answering (QA) over lengthy contexts is a significant challenge. In industrial settings, this process is often hindered by high computational costs and latency, especially when multiple questions must be answered based on the same context. In this work, we explore the capabilities of LLMs to answer multiple questions based on the same conversatio… ▽ More Deploying Large Language Models (LLMs) for question answering (QA) over lengthy contexts is a significant challenge. In industrial settings, this process is often hindered by high computational costs and latency, especially when multiple questions must be answered based on the same context. In this work, we explore the capabilities of LLMs to answer multiple questions based on the same conversational context. We conduct extensive experiments and benchmark a range of both proprietary and public models on this challenging task. Our findings highlight that while strong proprietary LLMs like GPT-4o achieve the best overall performance, fine-tuned public LLMs with up to 8 billion parameters can surpass GPT-4o in accuracy, which demonstrates their potential for transparent and cost-effective deployment in real-world applications. △ Less

Submitted 25 September, 2025; originally announced September 2025.

Comments: Accepted by EMNLP 2025 Industry Track

Accelerated Proton Resonance Frequency-based Magnetic Resonance Thermometry by Optimized Deep Learning Method

Authors: Sijie Xu, Shenyan Zong, Chang-Sheng Mei, Guofeng Shen, Yueran Zhao, He Wang

Abstract: Proton resonance frequency (PRF) based MR thermometry is essential for focused ultrasound (FUS) thermal ablation therapies. This work aims to enhance temporal resolution in dynamic MR temperature map reconstruction using an improved deep learning method. The training-optimized methods and five classical neural networks were applied on the 2-fold and 4-fold under-sampling k-space data to reconstruc… ▽ More Proton resonance frequency (PRF) based MR thermometry is essential for focused ultrasound (FUS) thermal ablation therapies. This work aims to enhance temporal resolution in dynamic MR temperature map reconstruction using an improved deep learning method. The training-optimized methods and five classical neural networks were applied on the 2-fold and 4-fold under-sampling k-space data to reconstruct the temperature maps. The enhanced training modules included offline/online data augmentations, knowledge distillation, and the amplitude-phase decoupling loss function. The heating experiments were performed by a FUS transducer on phantom and ex vivo tissues, respectively. These data were manually under-sampled to imitate acceleration procedures and trained in our method to get the reconstruction model. The additional dozen or so testing datasets were separately obtained for evaluating the real-time performance and temperature accuracy. Acceleration factors of 1.9 and 3.7 were found for 2 times and 4 times k-space under-sampling strategies and the ResUNet-based deep learning reconstruction performed exceptionally well. In 2-fold acceleration scenario, the RMSE of temperature map patches provided the values of 0.888 degree centigrade and 1.145 degree centigrade on phantom and ex vivo testing datasets. The DICE value of temperature areas enclosed by 43 degree centigrade isotherm was 0.809, and the Bland-Altman analysis showed a bias of -0.253 degree centigrade with the apart of plus or minus 2.16 degree centigrade. In 4 times under-sampling case, these evaluating values decreased by approximately 10%. This study demonstrates that deep learning-based reconstruction can significantly enhance the accuracy and efficiency of MR thermometry for clinical FUS thermal therapies. △ Less

Submitted 3 July, 2024; originally announced July 2024.

Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogism

Authors: Shi Zong, Jimmy Lin

Abstract: There have been a huge number of benchmarks proposed to evaluate how large language models (LLMs) behave for logic inference tasks. However, it remains an open question how to properly evaluate this ability. In this paper, we provide a systematic overview of prior works on the logical reasoning ability of LLMs for analyzing categorical syllogisms. We first investigate all the possible variations f… ▽ More There have been a huge number of benchmarks proposed to evaluate how large language models (LLMs) behave for logic inference tasks. However, it remains an open question how to properly evaluate this ability. In this paper, we provide a systematic overview of prior works on the logical reasoning ability of LLMs for analyzing categorical syllogisms. We first investigate all the possible variations for the categorical syllogisms from a purely logical perspective and then examine the underlying configurations (i.e., mood and figure) tested by the existing datasets. Our results indicate that compared to template-based synthetic datasets, crowdsourcing approaches normally sacrifice the coverage of configurations (i.e., mood and figure) of categorical syllogisms for more language variations, thus bringing challenges to fully testing LLMs under different situations. We then proceed to summarize the findings and observations for the performances of LLMs to infer the validity of syllogisms from the current literature. The error rate breakdown analyses suggest that the interpretation of the quantifiers seems to be the current bottleneck that limits the performances of the LLMs and is thus worth more attention. Finally, we discuss several points that might be worth considering when researchers plan on the future release of categorical syllogism datasets. We hope our work will not only provide a timely review of the current literature regarding categorical syllogisms, but also motivate more interdisciplinary research between communities, specifically computational linguists and logicians. △ Less

Submitted 11 December, 2024; v1 submitted 26 June, 2024; originally announced June 2024.

Comments: camera-ready version

ADS-Cap: A Framework for Accurate and Diverse Stylized Captioning with Unpaired Stylistic Corpora

Authors: Kanzhi Cheng, Zheng Ma, Shi Zong, Jianbing Zhang, Xinyu Dai, Jiajun Chen

Abstract: Generating visually grounded image captions with specific linguistic styles using unpaired stylistic corpora is a challenging task, especially since we expect stylized captions with a wide variety of stylistic patterns. In this paper, we propose a novel framework to generate Accurate and Diverse Stylized Captions (ADS-Cap). Our ADS-Cap first uses a contrastive learning module to align the image an… ▽ More Generating visually grounded image captions with specific linguistic styles using unpaired stylistic corpora is a challenging task, especially since we expect stylized captions with a wide variety of stylistic patterns. In this paper, we propose a novel framework to generate Accurate and Diverse Stylized Captions (ADS-Cap). Our ADS-Cap first uses a contrastive learning module to align the image and text features, which unifies paired factual and unpaired stylistic corpora during the training process. A conditional variational auto-encoder is then used to automatically memorize diverse stylistic patterns in latent space and enhance diversity through sampling. We also design a simple but effective recheck module to boost style accuracy by filtering style-specific captions. Experimental results on two widely used stylized image captioning datasets show that regarding consistency with the image, style accuracy and diversity, ADS-Cap achieves outstanding performances compared to various baselines. We finally conduct extensive analyses to understand the effectiveness of our method. Our code is available at https://github.com/njucckevin/ADS-Cap. △ Less

Submitted 2 August, 2023; originally announced August 2023.

Comments: Accepted at Natural Language Processing and Chinese Computing (NLPCC) 2022

$SmartProbe$: A Virtual Moderator for Market Research Surveys

Authors: Josh Seltzer, Jiahua Pan, Kathy Cheng, Yuxiao Sun, Santosh Kolagati, Jimmy Lin, Shi Zong

Abstract: Market research surveys are a powerful methodology for understanding consumer perspectives at scale, but are limited by depth of understanding and insights. A virtual moderator can introduce elements of qualitative research into surveys, developing a rapport with survey participants and dynamically asking probing questions, ultimately to elicit more useful information for market researchers. In th… ▽ More Market research surveys are a powerful methodology for understanding consumer perspectives at scale, but are limited by depth of understanding and insights. A virtual moderator can introduce elements of qualitative research into surveys, developing a rapport with survey participants and dynamically asking probing questions, ultimately to elicit more useful information for market researchers. In this work, we introduce ${\tt SmartProbe}$, an API which leverages the adaptive capabilities of large language models (LLMs), and incorporates domain knowledge from market research, in order to generate effective probing questions in any market research survey. We outline the modular processing flow of $\tt SmartProbe$, and evaluate the quality and effectiveness of its generated probing questions. We believe our efforts will inspire industry practitioners to build real-world applications based on the latest advances in LLMs. Our demo is publicly available at https://nexxt.in/smartprobe-demo △ Less

Submitted 14 May, 2023; originally announced May 2023.

Which Model Shall I Choose? Cost/Quality Trade-offs for Text Classification Tasks

Authors: Shi Zong, Josh Seltzer, Jiahua, Pan, Kathy Cheng, Jimmy Lin

Abstract: Industry practitioners always face the problem of choosing the appropriate model for deployment under different considerations, such as to maximize a metric that is crucial for production, or to reduce the total cost given financial concerns. In this work, we focus on the text classification task and present a quantitative analysis for this challenge. Using classification accuracy as the main metr… ▽ More Industry practitioners always face the problem of choosing the appropriate model for deployment under different considerations, such as to maximize a metric that is crucial for production, or to reduce the total cost given financial concerns. In this work, we focus on the text classification task and present a quantitative analysis for this challenge. Using classification accuracy as the main metric, we evaluate the classifiers' performances for a variety of models, including large language models, along with their associated costs, including the annotation cost, training (fine-tuning) cost, and inference cost. We then discuss the model choices for situations like having a large number of samples needed for inference. We hope our work will help people better understand the cost/quality trade-offs for the text classification task. △ Less

Submitted 17 January, 2023; originally announced January 2023.

Probing Cross-modal Semantics Alignment Capability from the Textual Perspective

Authors: Zheng Ma, Shi Zong, Mianzhi Pan, Jianbing Zhang, Shujian Huang, Xinyu Dai, Jiajun Chen

Abstract: In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks. Aligning cross-modal semantics is claimed to be one of the essential capabilities of VLP models. However, it still remains unclear about the inner working mechanism of alignment in VLP models. In this paper, we propose a new probing method that is… ▽ More In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks. Aligning cross-modal semantics is claimed to be one of the essential capabilities of VLP models. However, it still remains unclear about the inner working mechanism of alignment in VLP models. In this paper, we propose a new probing method that is based on image captioning to first empirically study the cross-modal semantics alignment of VLP models. Our probing method is built upon the fact that given an image-caption pair, the VLP models will give a score, indicating how well two modalities are aligned; maximizing such scores will generate sentences that VLP models believe are of good alignment. Analyzing these sentences thus will reveal in what way different modalities are aligned and how well these alignments are in VLP models. We apply our probing method to five popular VLP models, including UNITER, ROSITA, ViLBERT, CLIP, and LXMERT, and provide a comprehensive analysis of the generated captions guided by these models. Our results show that VLP models (1) focus more on just aligning objects with visual words, while neglecting global semantics; (2) prefer fixed sentence patterns, thus ignoring more important textual information including fluency and grammar; and (3) deem the captions with more visual words are better aligned with images. These findings indicate that VLP models still have weaknesses in cross-modal semantics alignment and we hope this work will draw researchers' attention to such problems when designing a new VLP model. △ Less

Submitted 17 October, 2022; originally announced October 2022.

Comments: Findings of EMNLP2022

Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings

Authors: Zhihuan Kuang, Shi Zong, Jianbing Zhang, Jiajun Chen, Hongfu Liu

Abstract: In this paper, we consider a novel research problem: music-to-text synaesthesia. Different from the classical music tagging problem that classifies a music recording into pre-defined categories, music-to-text synaesthesia aims to generate descriptive texts from music recordings with the same sentiment for further understanding. As existing music-related datasets do not contain the semantic descrip… ▽ More In this paper, we consider a novel research problem: music-to-text synaesthesia. Different from the classical music tagging problem that classifies a music recording into pre-defined categories, music-to-text synaesthesia aims to generate descriptive texts from music recordings with the same sentiment for further understanding. As existing music-related datasets do not contain the semantic descriptions on music recordings, we collect a new dataset that contains 1,955 aligned pairs of classical music recordings and text descriptions. Based on this, we build a computational model to generate sentences that can describe the content of the music recording. To tackle the highly non-discriminative classical music, we design a group topology-preservation loss, which considers more samples as a group reference and preserves the relative topology among different samples. Extensive experimental results qualitatively and quantitatively demonstrate the effectiveness of our proposed model over five heuristics or pre-trained competitive methods and their variants on our collected dataset. △ Less

Submitted 7 May, 2023; v1 submitted 2 October, 2022; originally announced October 2022.

Characterizing player's playing styles based on Player Vectors for each playing position in the Chinese Football Super League

Authors: Yuesen Li, Shouxin Zong, Yanfei Shen, Zhiqiang Pu, Miguel-Ángel Gómez, Yixiong Cui

Abstract: Characterizing playing style is important for football clubs on scouting, monitoring and match preparation. Previous studies considered a player's style as a combination of technical performances, failing to consider the spatial information. Therefore, this study aimed to characterize the playing styles of each playing position in the Chinese Football Super League (CSL) matches, integrating a rece… ▽ More Characterizing playing style is important for football clubs on scouting, monitoring and match preparation. Previous studies considered a player's style as a combination of technical performances, failing to consider the spatial information. Therefore, this study aimed to characterize the playing styles of each playing position in the Chinese Football Super League (CSL) matches, integrating a recently adopted Player Vectors framework. Data of 960 matches from 2016-2019 CSL were used. Match ratings, and ten types of match events with the corresponding coordinates for all the lineup players whose on-pitch time exceeded 45 minutes were extracted. Players were first clustered into 8 positions. A player vector was constructed for each player in each match based on the Player Vectors using Nonnegative Matrix Factorization (NMF). Another NMF process was run on the player vectors to extract different types of playing styles. The resulting player vectors discovered 18 different playing styles in the CSL. Six performance indicators of each style were investigated to observe their contributions. In general, the playing styles of forwards and midfielders are in line with football performance evolution trends, while the styles of defenders should be reconsidered. Multifunctional playing styles were also found in high rated CSL players. △ Less

Submitted 7 July, 2022; v1 submitted 5 May, 2022; originally announced May 2022.

Comments: 40 pages, 5 figures, already published on Journal of Sports Sciences

ACM Class: I.2.1

Analyzing the Intensity of Complaints on Social Media

Authors: Ming Fang, Shi Zong, Jing Li, Xinyu Dai, Shujian Huang, Jiajun Chen

Abstract: Complaining is a speech act that expresses a negative inconsistency between reality and human expectations. While prior studies mostly focus on identifying the existence or the type of complaints, in this work, we present the first study in computational linguistics of measuring the intensity of complaints from text. Analyzing complaints from such perspective is particularly useful, as complaints… ▽ More Complaining is a speech act that expresses a negative inconsistency between reality and human expectations. While prior studies mostly focus on identifying the existence or the type of complaints, in this work, we present the first study in computational linguistics of measuring the intensity of complaints from text. Analyzing complaints from such perspective is particularly useful, as complaints of certain degrees may cause severe consequences for companies or organizations. We create the first Chinese dataset containing 3,103 posts about complaints from Weibo, a popular Chinese social media platform. These posts are then annotated with complaints intensity scores using Best-Worst Scaling (BWS) method. We show that complaints intensity can be accurately estimated by computational models with the best mean square error achieving 0.11. Furthermore, we conduct a comprehensive linguistic analysis around complaints, including the connections between complaints and sentiment, and a cross-lingual comparison for complaints expressions used by Chinese and English speakers. We finally show that our complaints intensity scores can be incorporated for better estimating the popularity of posts on social media. △ Less

Submitted 20 April, 2022; originally announced April 2022.

Comments: NAACL 2022 (Findings)

Doctor Recommendation in Online Health Forums via Expertise Learning

Authors: Xiaoxin Lu, Yubo Zhang, Jing Li, Shi Zong

Abstract: Huge volumes of patient queries are daily generated on online health forums, rendering manual doctor allocation a labor-intensive task. To better help patients, this paper studies a novel task of doctor recommendation to enable automatic pairing of a patient to a doctor with relevant expertise. While most prior work in recommendation focuses on modeling target users from their past behavior, we ca… ▽ More Huge volumes of patient queries are daily generated on online health forums, rendering manual doctor allocation a labor-intensive task. To better help patients, this paper studies a novel task of doctor recommendation to enable automatic pairing of a patient to a doctor with relevant expertise. While most prior work in recommendation focuses on modeling target users from their past behavior, we can only rely on the limited words in a query to infer a patient's needs for privacy reasons. For doctor modeling, we study the joint effects of their profiles and previous dialogues with other patients and explore their interactions via self-learning. The learned doctor embeddings are further employed to estimate their capabilities of handling a patient query with a multi-head attention mechanism. For experiments, a large-scale dataset is collected from Chunyu Yisheng, a Chinese online health forum, where our model exhibits the state-of-the-art results, outperforming baselines only consider profiles and past dialogues to characterize a doctor. △ Less

Submitted 14 March, 2022; v1 submitted 6 March, 2022; originally announced March 2022.

Comments: Accepted to ACL 2022 main conference

Faster Nearest Neighbor Machine Translation

Authors: Shuhe Wang, Jiwei Li, Yuxian Meng, Rongbin Ouyang, Guoyin Wang, Xiaoya Li, Tianwei Zhang, Shi Zong

Abstract: $k$NN based neural machine translation ($k$NN-MT) has achieved state-of-the-art results in a variety of MT tasks. One significant shortcoming of $k$NN-MT lies in its inefficiency in identifying the $k$ nearest neighbors of the query representation from the entire datastore, which is prohibitively time-intensive when the datastore size is large. In this work, we propose \textbf{Faster $k… ▽ More $k$NN based neural machine translation ($k$NN-MT) has achieved state-of-the-art results in a variety of MT tasks. One significant shortcoming of $k$NN-MT lies in its inefficiency in identifying the $k$ nearest neighbors of the query representation from the entire datastore, which is prohibitively time-intensive when the datastore size is large. In this work, we propose \textbf{Faster $k$NN-MT} to address this issue. The core idea of Faster $k$NN-MT is to use a hierarchical clustering strategy to approximate the distance between the query and a data point in the datastore, which is decomposed into two parts: the distance between the query and the center of the cluster that the data point belongs to, and the distance between the data point and the cluster center. We propose practical ways to compute these two parts in a significantly faster manner. Through extensive experiments on different MT benchmarks, we show that \textbf{Faster $k$NN-MT} is faster than Fast $k$NN-MT \citep{meng2021fast} and only slightly (1.2 times) slower than its vanilla counterpart while preserving model performance as $k$NN-MT. Faster $k$NN-MT enables the deployment of $k$NN-MT models on real-world MT services. △ Less

Submitted 15 December, 2021; originally announced December 2021.

GNN-LM: Language Modeling based on Global Contexts via GNN

Authors: Yuxian Meng, Shi Zong, Xiaoya Li, Xiaofei Sun, Tianwei Zhang, Fei Wu, Jiwei Li

Abstract: Inspired by the notion that ``{\it to copy is easier than to memorize}``, in this work, we introduce GNN-LM, which extends the vanilla neural language model (LM) by allowing to reference similar contexts in the entire training corpus. We build a directed heterogeneous graph between an input context and its semantically related neighbors selected from the training corpus, where nodes are tokens in… ▽ More Inspired by the notion that ``{\it to copy is easier than to memorize}``, in this work, we introduce GNN-LM, which extends the vanilla neural language model (LM) by allowing to reference similar contexts in the entire training corpus. We build a directed heterogeneous graph between an input context and its semantically related neighbors selected from the training corpus, where nodes are tokens in the input context and retrieved neighbor contexts, and edges represent connections between nodes. Graph neural networks (GNNs) are constructed upon the graph to aggregate information from similar contexts to decode the token. This learning paradigm provides direct access to the reference contexts and helps improve a model's generalization ability. We conduct comprehensive experiments to validate the effectiveness of the GNN-LM: GNN-LM achieves a new state-of-the-art perplexity of 14.8 on WikiText-103 (a 3.9 point improvement over its counterpart of the vanilla LM model), and shows substantial improvement on One Billion Word and Enwiki8 datasets against strong baselines. In-depth ablation studies are performed to understand the mechanics of GNN-LM. \footnote{The code can be found at https://github.com/ShannonAI/GNN-LM △ Less

Submitted 4 May, 2022; v1 submitted 17 October, 2021; originally announced October 2021.

Comments: To appear at ICLR 2022

Towards Safer Transportation: a self-supervised learning approach for traffic video deraining

Authors: Shuya Zong, Sikai Chen, Samuel Labi

Abstract: Video monitoring of traffic is useful for traffic management and control, traffic counting, and traffic law enforcement. However, traffic monitoring during inclement weather such as rain is a challenging task because video quality is corrupted by streaks of falling rain on the video image, and this hinders reliable characterization not only of the road environment but also of road-user behavior du… ▽ More Video monitoring of traffic is useful for traffic management and control, traffic counting, and traffic law enforcement. However, traffic monitoring during inclement weather such as rain is a challenging task because video quality is corrupted by streaks of falling rain on the video image, and this hinders reliable characterization not only of the road environment but also of road-user behavior during such adverse weather events. This study proposes a two-stage self-supervised learning method to remove rain streaks in traffic videos. The first and second stages address intra- and inter-frame noise, respectively. The results indicated that the model exhibits satisfactory performance in terms of the image visual quality and the Peak Signal-Noise Ratio value. △ Less

Submitted 11 October, 2021; originally announced October 2021.

Comments: Under review for presentation at TRB 2022 Annual Meeting

Using UAVs for vehicle tracking and collision risk assessment at intersections

Authors: Shuya Zong, Sikai Chen, Majed Alinizzi, Yujie Li, Samuel Labi

Abstract: Assessing collision risk is a critical challenge to effective traffic safety management. The deployment of unmanned aerial vehicles (UAVs) to address this issue has shown much promise, given their wide visual field and movement flexibility. This research demonstrates the application of UAVs and V2X connectivity to track the movement of road users and assess potential collisions at intersections. T… ▽ More Assessing collision risk is a critical challenge to effective traffic safety management. The deployment of unmanned aerial vehicles (UAVs) to address this issue has shown much promise, given their wide visual field and movement flexibility. This research demonstrates the application of UAVs and V2X connectivity to track the movement of road users and assess potential collisions at intersections. The study uses videos captured by UAVs. The proposed method combines deep-learning based tracking algorithms and time-to-collision tasks. The results not only provide beneficial information for vehicle's recognition of potential crashes and motion planning but also provided a valuable tool for urban road agencies and safety management engineers. △ Less

Submitted 11 October, 2021; originally announced October 2021.

Comments: Under review for presentation at TRB 2022 Annual Meeting

Development and testing of an image transformer for explainable autonomous driving systems

Authors: Jiqian Dong, Sikai Chen, Shuya Zong, Tiantian Chen, Mohammad Miralinaghi, Samuel Labi

Abstract: In the last decade, deep learning (DL) approaches have been used successfully in computer vision (CV) applications. However, DL-based CV models are generally considered to be black boxes due to their lack of interpretability. This black box behavior has exacerbated user distrust and therefore has prevented widespread deployment DLCV models in autonomous driving tasks even though some of these mode… ▽ More In the last decade, deep learning (DL) approaches have been used successfully in computer vision (CV) applications. However, DL-based CV models are generally considered to be black boxes due to their lack of interpretability. This black box behavior has exacerbated user distrust and therefore has prevented widespread deployment DLCV models in autonomous driving tasks even though some of these models exhibit superiority over human performance. For this reason, it is essential to develop explainable DL models for autonomous driving task. Explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify anydefects and weaknesses of the model during the system development phase. In this paper, we propose an explainable end-to-end autonomous driving system based on "Transformer", a state-of-the-art (SOTA) self-attention based model, to map visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations. The model achieves a soft attention over the global features of the image. The results demonstrate the efficacy of our proposed model as it exhibits superior performance (in terms of correct prediction of actions and explanations) compared to the benchmark model by a significant margin with lower computational cost. △ Less

Submitted 11 October, 2021; originally announced October 2021.

Comments: Under review for presentation at TRB 2022 Annual Meeting

Measuring Forecasting Skill from Text

Authors: Shi Zong, Alan Ritter, Eduard Hovy

Abstract: People vary in their ability to make accurate predictions about the future. Prior studies have shown that some individuals can predict the outcome of future events with consistently better accuracy. This leads to a natural question: what makes some forecasters better than others? In this paper we explore connections between the language people use to describe their predictions and their forecastin… ▽ More People vary in their ability to make accurate predictions about the future. Prior studies have shown that some individuals can predict the outcome of future events with consistently better accuracy. This leads to a natural question: what makes some forecasters better than others? In this paper we explore connections between the language people use to describe their predictions and their forecasting skill. Datasets from two different forecasting domains are explored: (1) geopolitical forecasts from Good Judgment Open, an online prediction forum and (2) a corpus of company earnings forecasts made by financial analysts. We present a number of linguistic metrics which are computed over text associated with people's predictions about the future including: uncertainty, readability, and emotion. By studying linguistic factors associated with predictions, we are able to shed some light on the approach taken by skilled forecasters. Furthermore, we demonstrate that it is possible to accurately predict forecasting skill using a model that is based solely on language. This could potentially be useful for identifying accurate predictions or potentially skilled forecasters earlier. △ Less

Submitted 16 June, 2020; v1 submitted 12 June, 2020; originally announced June 2020.

Comments: Accepted at ACL 2020

Extracting a Knowledge Base of COVID-19 Events from Social Media

Authors: Shi Zong, Ashutosh Baheti, Wei Xu, Alan Ritter

Abstract: In this paper, we present a manually annotated corpus of 10,000 tweets containing public reports of five COVID-19 events, including positive and negative tests, deaths, denied access to testing, claimed cures and preventions. We designed slot-filling questions for each event type and annotated a total of 31 fine-grained slots, such as the location of events, recent travel, and close contacts. We s… ▽ More In this paper, we present a manually annotated corpus of 10,000 tweets containing public reports of five COVID-19 events, including positive and negative tests, deaths, denied access to testing, claimed cures and preventions. We designed slot-filling questions for each event type and annotated a total of 31 fine-grained slots, such as the location of events, recent travel, and close contacts. We show that our corpus can support fine-tuning BERT-based classifiers to automatically extract publicly reported events and help track the spread of a new disease. We also demonstrate that, by aggregating events extracted from millions of tweets, we achieve surprisingly high precision when answering complex queries, such as "Which organizations have employees that tested positive in Philadelphia?" We will release our corpus (with user-information removed), automatic extraction models, and the corresponding knowledge base to the research community. △ Less

Submitted 9 September, 2022; v1 submitted 3 June, 2020; originally announced June 2020.

Comments: Accepted at COLING 2022

Analyzing the Perceived Severity of Cybersecurity Threats Reported on Social Media

Authors: Shi Zong, Alan Ritter, Graham Mueller, Evan Wright

Abstract: Breaking cybersecurity events are shared across a range of websites, including security blogs (FireEye, Kaspersky, etc.), in addition to social media platforms such as Facebook and Twitter. In this paper, we investigate methods to analyze the severity of cybersecurity threats based on the language that is used to describe them online. A corpus of 6,000 tweets describing software vulnerabilities is… ▽ More Breaking cybersecurity events are shared across a range of websites, including security blogs (FireEye, Kaspersky, etc.), in addition to social media platforms such as Facebook and Twitter. In this paper, we investigate methods to analyze the severity of cybersecurity threats based on the language that is used to describe them online. A corpus of 6,000 tweets describing software vulnerabilities is annotated with authors' opinions toward their severity. We show that our corpus supports the development of automatic classifiers with high precision for this task. Furthermore, we demonstrate the value of analyzing users' opinions about the severity of threats reported online as an early indicator of important software vulnerabilities. We present a simple, yet effective method for linking software vulnerabilities reported in tweets to Common Vulnerabilities and Exposures (CVEs) in the National Vulnerability Database (NVD). Using our predicted severity scores, we show that it is possible to achieve a Precision@50 of 0.86 when forecasting high severity vulnerabilities, significantly outperforming a baseline that is based on tweet volume. Finally we show how reports of severe vulnerabilities online are predictive of real-world exploits. △ Less

Submitted 3 May, 2019; v1 submitted 27 February, 2019; originally announced February 2019.

Comments: Accepted at NAACL 2019

Does Weather Matter? Causal Analysis of TV Logs

Authors: Shi Zong, Branislav Kveton, Shlomo Berkovsky, Azin Ashkan, Nikos Vlassis, Zheng Wen

Abstract: Weather affects our mood and behaviors, and many aspects of our life. When it is sunny, most people become happier; but when it rains, some people get depressed. Despite this evidence and the abundance of data, weather has mostly been overlooked in the machine learning and data science research. This work presents a causal analysis of how weather affects TV watching patterns. We show that some wea… ▽ More Weather affects our mood and behaviors, and many aspects of our life. When it is sunny, most people become happier; but when it rains, some people get depressed. Despite this evidence and the abundance of data, weather has mostly been overlooked in the machine learning and data science research. This work presents a causal analysis of how weather affects TV watching patterns. We show that some weather attributes, such as pressure and precipitation, cause major changes in TV watching patterns. To the best of our knowledge, this is the first large-scale causal study of the impact of weather on TV watching patterns. △ Less

Submitted 24 March, 2017; v1 submitted 25 January, 2017; originally announced January 2017.

Comments: Companion of the 26th International World Wide Web Conference

Multi-pretrained Deep Neural Network

Authors: Zhen Hu, Zhuyin Xue, Tong Cui, Shiqiang Zong, Chenglong He

Abstract: Pretraining is widely used in deep neutral network and one of the most famous pretraining models is Deep Belief Network (DBN). The optimization formulas are different during the pretraining process for different pretraining models. In this paper, we pretrained deep neutral network by different pretraining models and hence investigated the difference between DBN and Stacked Denoising Autoencoder (S… ▽ More Pretraining is widely used in deep neutral network and one of the most famous pretraining models is Deep Belief Network (DBN). The optimization formulas are different during the pretraining process for different pretraining models. In this paper, we pretrained deep neutral network by different pretraining models and hence investigated the difference between DBN and Stacked Denoising Autoencoder (SDA) when used as pretraining model. The experimental results show that DBN get a better initial model. However the model converges to a relatively worse model after the finetuning process. Yet after pretrained by SDA for the second time the model converges to a better model if finetuned. △ Less

Submitted 2 June, 2016; originally announced June 2016.

Detecting Localized Categorical Attributes on Graphs

Authors: Siheng Chen, Yaoqing Yang, Shi Zong, Aarti Singh, Jelena Kovačević

Abstract: Do users from Carnegie Mellon University form social communities on Facebook? Do signal processing researchers from tightly collaborate with each other? Do Chinese restaurants in Manhattan cluster together? These seemingly different problems share a common structure: an attribute that may be localized on a graph. In other words, nodes activated by an attribute form a subgraph that can be easily se… ▽ More Do users from Carnegie Mellon University form social communities on Facebook? Do signal processing researchers from tightly collaborate with each other? Do Chinese restaurants in Manhattan cluster together? These seemingly different problems share a common structure: an attribute that may be localized on a graph. In other words, nodes activated by an attribute form a subgraph that can be easily separated from other nodes. In this paper, we thus focus on the task of detecting localized attributes on a graph. We are particularly interested in categorical attributes such as attributes in online social networks, ratings in recommender systems and viruses in cyber-physical systems because they are widely used in numerous data mining applications. To solve the task, we formulate a statistical hypothesis testing problem to decide whether a given attribute is localized or not. We propose two statistics: graph wavelet statistic and graph scan statistic, both of which are provably effective in detecting localized attributes. We validate the robustness of the proposed statistics on both simulated data and two real-world applications: high air-pollution detection and keyword ranking in a co-authorship network collected from IEEE Xplore. Experimental results show that the proposed graph wavelet statistic and graph scan statistic are effective and efficient. △ Less

Submitted 11 February, 2017; v1 submitted 3 April, 2016; originally announced April 2016.

Comments: Accepted for publication in the IEEE Transactions on Signal Processing

Cascading Bandits for Large-Scale Recommendation Problems

Authors: Shi Zong, Hao Ni, Kenny Sung, Nan Rosemary Ke, Zheng Wen, Branislav Kveton

Abstract: Most recommender systems recommend a list of items. The user examines the list, from the first item to the last, and often chooses the first attractive item and does not examine the rest. This type of user behavior can be modeled by the cascade model. In this work, we study cascading bandits, an online learning variant of the cascade model where the goal is to recommend $K$ most attractive items f… ▽ More Most recommender systems recommend a list of items. The user examines the list, from the first item to the last, and often chooses the first attractive item and does not examine the rest. This type of user behavior can be modeled by the cascade model. In this work, we study cascading bandits, an online learning variant of the cascade model where the goal is to recommend $K$ most attractive items from a large set of $L$ candidate items. We propose two algorithms for solving this problem, which are based on the idea of linear generalization. The key idea in our solutions is that we learn a predictor of the attraction probabilities of items from their features, as opposing to learning the attraction probability of each item independently as in the existing work. This results in practical learning algorithms whose regret does not depend on the number of items $L$. We bound the regret of one algorithm and comprehensively evaluate the other on a range of recommendation problems. The algorithm performs well and outperforms all baselines. △ Less

Submitted 30 June, 2016; v1 submitted 17 March, 2016; originally announced March 2016.

Comments: Accepted to UAI 2016