arXiv subjects

Mingyang Zhou

Publications and source records attributed to Mingyang Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2024

Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning

Recent advancements in large vision-language models (LVLMs) have led to significant progress in generating natural language descriptions for visual content and thus enhancing various applications. One issue with these powerful models is that they sometimes produce texts that are factually inconsistent with the visual input. While there has been some effort to mitigate such inconsistencies in natural image captioning, the factuality of generated captions for structured document images, such as charts, has not received as much scrutiny, posing a potential threat to information reliability in critical applications. This work delves into the factuality aspect by introducing a comprehensive typology of factual errors in generated chart captions. A large-scale human annotation effort provides insight into the error patterns and frequencies in captions crafted by various chart captioning models, ultimately forming the foundation of a novel dataset, CHOCOLATE. Our analysis reveals that even state-of-the-art models, including GPT-4V, frequently produce captions laced with factual inaccuracies. In response to this challenge, we establish the new task of Chart Caption Factual Error Correction and introduce CHARTVE, a model for visual entailment that outperforms proprietary and open-source LVLMs in evaluating factual consistency. Furthermore, we propose C2TFEC, an interpretable two-stage framework that excels at correcting factual errors. This work inaugurates a new domain in factual error correction for chart captions, presenting a novel evaluation mechanism, and demonstrating an effective approach to ensuring the factuality of generated chart captions. The code and data as well as the continuously updated benchmark can be found at: https://khuangaf.github.io/CHOCOLATE/.

cs.CL↗

arXiv2023

Explainable Recommendation with Personalized Review Retrieval and Aspect Learning

Explainable recommendation is a technique that combines prediction and generation tasks to produce more persuasive results. Among these tasks, textual generation demands large amounts of data to achieve satisfactory accuracy. However, historical user reviews of items are often insufficient, making it challenging to ensure the precision of generated explanation text. To address this issue, we propose a novel model, ERRA (Explainable Recommendation by personalized Review retrieval and Aspect learning). With retrieval enhancement, ERRA can obtain additional information from the training sets. With this additional information, we can generate more accurate and informative explanations. Furthermore, to better capture users' preferences, we incorporate an aspect enhancement component into our model. By selecting the top-n aspects that users are most concerned about for different items, we can model user representation with more relevant details, making the explanation more persuasive. To verify the effectiveness of our model, extensive experiments on three datasets show that our model outperforms state-of-the-art baselines (for example, 3.4% improvement in prediction and 15.8% improvement in explanation for TripAdvisor).

cs.SI↗

arXiv2023

Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs

Building cross-model intelligence that can understand charts and communicate the salient information hidden behind them is an appealing challenge in the vision and language(V+L) community. The capability to uncover the underlined table data of chart figures is a critical key to automatic chart understanding. We introduce ChartT5, a V+L model that learns how to interpret table information from chart images via cross-modal pre-training on plot table pairs. Specifically, we propose two novel pre-training objectives: Masked Header Prediction (MHP) and Masked Value Prediction (MVP) to facilitate the model with different skills to interpret the table information. We have conducted extensive experiments on chart question answering and chart summarization to verify the effectiveness of the proposed pre-training strategies. In particular, on the ChartQA benchmark, our ChartT5 outperforms the state-of-the-art non-pretraining methods by over 8% performance gains.

cs.CL↗

arXiv2022

Focus! Relevant and Sufficient Context Selection for News Image Captioning

News Image Captioning requires describing an image by leveraging additional context from a news article. Previous works only coarsely leverage the article to extract the necessary context, which makes it challenging for models to identify relevant events and named entities. In our paper, we first demonstrate that by combining more fine-grained context that captures the key named entities (obtained via an oracle) and the global context that summarizes the news, we can dramatically improve the model's ability to generate accurate news captions. This begs the question, how to automatically extract such key entities from an image? We propose to use the pre-trained vision and language retrieval model CLIP to localize the visually grounded entities in the news article and then capture the non-visual entities via an open relation extraction model. Our experiments demonstrate that by simply selecting a better context from the article, we can significantly improve the performance of existing models and achieve new state-of-the-art performance on multiple benchmarks.

cs.CV↗

arXiv2022

Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment

Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data, which is costly to collect, compared to image-only or text-only data. In this paper, we explore unsupervised Vision-and-Language pre-training (UVLP) to learn the cross-modal representation from non-parallel image and text datasets. We found two key factors that lead to good unsupervised V+L pre-training without parallel data: (i) joint image-and-text input (ii) overall image-text alignment (even for non-parallel data). Accordingly, we propose a novel unsupervised V+L pre-training curriculum for non-parallel texts and images. We first construct a weakly aligned image-text corpus via a retrieval-based approach, then apply a set of multi-granular alignment pre-training tasks, including region-to-tag, region-to-phrase, and image-to-sentence alignment, to bridge the gap between the two modalities. A comprehensive ablation study shows each granularity is helpful to learn a stronger pre-trained model. We adapt our pre-trained model to a set of V+L downstream tasks, including VQA, NLVR2, Visual Entailment, and RefCOCO+. Our model achieves the state-of-art performance in all these tasks under the unsupervised setting.

cs.CV↗

arXiv2022

Epidemic Plateau: A Phenomenon under Adaptive Prevention Strategies

Since the beginning of the COVID-19 spreading, the number of studies on the epidemic models increased dramatically. It is important for policymakers to know how the disease will spread and what are the effects of the policies and environment on the spreading. In this paper, we propose two extensions to the standard SIR model: (a) we consider the prevention measures adopted based on the current severity of the infection. Those measures are adaptive and change over time; (b) multiple cities and regions are considered, with population movements between those cities and regions, while taking into account that each region may have different prevention measures. Although the adaptive measures and mobility of the population were often observed during the pandemic, these effects are rarely explicitly modeled and studied in the classical epidemic models. The model we propose gives rise to a plateau phenomenon: the number of people infected by the disease stays at the same level during an extended period of time. We show what are conditions need to be met in order for the spreading to exhibit a plateau period in a single city. In addition, this phenomenon is interdependent when considering multiple cities. We verify from the real-world data that the plateau phenomenon does exist in many regions of the world in the current COVID-19 development. Finally, we provide theoretical analysis on the plateau phenomenon for the single-city model and derive a series of results on the emergence and the ending of the plateau, as well as on the height and length of the plateau. Our theoretical results match well with our experimental findings.

physics.soc-ph↗

arXiv2021

Insta-VAX: A Multimodal Benchmark for Anti-Vaccine and Misinformation Posts Detection on Social Media

Sharing of anti-vaccine posts on social media, including misinformation posts, has been shown to create confusion and reduce the publics confidence in vaccines, leading to vaccine hesitancy and resistance. Recent years have witnessed the fast rise of such anti-vaccine posts in a variety of linguistic and visual forms in online networks, posing a great challenge for effective content moderation and tracking. Extending previous work on leveraging textual information to understand vaccine information, this paper presents Insta-VAX, a new multi-modal dataset consisting of a sample of 64,957 Instagram posts related to human vaccines. We applied a crowdsourced annotation procedure verified by two trained expert judges to this dataset. We then bench-marked several state-of-the-art NLP and computer vision classifiers to detect whether the posts show anti-vaccine attitude and whether they contain misinformation. Extensive experiments and analyses demonstrate the multimodal models can classify the posts more accurately than the uni-modal models, but still need improvement especially on visual context understanding and external knowledge cooperation. The dataset and classifiers contribute to monitoring and tracking of vaccine discussions for social scientific and public health efforts in combating the problem of vaccine misinformation.

cs.CL↗

arXiv2021

Proposal of Analog In-Memory Computing with Magnified Tunnel Magnetoresistance Ratio and Universal STT-MRAM Cell

In-memory computing (IMC) is an effectual solution for energy-efficient artificial intelligence applications. Analog IMC amortizes the power consumption of multiple sensing amplifiers with analog-to-digital converter (ADC), and simultaneously completes the calculation of multi-line data with high parallelism degree. Based on a universal one-transistor one-magnetic tunnel junction (MTJ) spin transfer torque magnetic RAM (STT-MRAM) cell, this paper demonstrates a novel tunneling magnetoresistance (TMR) ratio magnifying method to realize analog IMC. Previous concerns include low TMR ratio and analog calculation nonlinearity are addressed using device-circuit interaction. Peripheral circuits are minimally modified to enable in-memory matrix-vector multiplication. A current mirror with feedback structure is implemented to enhance analog computing linearity and calculation accuracy. The proposed design maximumly supports 1024 2-bit input and 1-bit weight multiply-and-accumulate (MAC) computations simultaneously. The 2-bit input is represented by the width of the input (IN) pulses, while the 1-bit weight is stored in STT-MRAM and the x7500 magnified TMR (m-TMR) ratio is obtained by latching. The proposal is simulated using 28-nm CMOS process and MTJ compact model. The integral nonlinearity is reduced by 57.6% compared with the conventional structure. 9.47-25.4 TOPS/W is realized with 2-bit input, 1-bit weight and 4-bit output convolution neural network (CNN).

cs.ET↗

arXiv2021

UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training

Vision-and-language pre-training has achieved impressive success in learning multimodal representations between vision and language. To generalize this success to non-English languages, we introduce UC2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning. To tackle the scarcity problem of multilingual captions for image datasets, we first augment existing English-only datasets with other languages via machine translation (MT). Then we extend the standard Masked Language Modeling and Image-Text Matching training objectives to multilingual setting, where alignment between different languages is captured through shared visual context (i.e, using image as pivot). To facilitate the learning of a joint embedding space of images and all languages of interest, we further propose two novel pre-training tasks, namely Masked Region-to-Token Modeling (MRTM) and Visual Translation Language Modeling (VTLM), leveraging MT-enhanced translated data. Evaluation on multilingual image-text retrieval and multilingual visual question answering benchmarks demonstrates that our proposed framework achieves new state-of-the-art on diverse non-English benchmarks while maintaining comparable performance to monolingual pre-trained models on English tasks.

cs.CV↗

arXiv2020

Gunrock 2.0: A User Adaptive Social Conversational System

Gunrock 2.0 is built on top of Gunrock with an emphasis on user adaptation. Gunrock 2.0 combines various neural natural language understanding modules, including named entity detection, linking, and dialog act prediction, to improve user understanding. Its dialog management is a hierarchical model that handles various topics, such as movies, music, and sports. The system-level dialog manager can handle question detection, acknowledgment, error handling, and additional functions, making downstream modules much easier to design and implement. The dialog manager also adapts its topic selection to accommodate different users' profile information, such as inferred gender and personality. The generation model is a mix of templates and neural generation models. Gunrock 2.0 is able to achieve an average rating of 3.73 at its latest build from May 29th to June 4th.

cs.CL↗

arXiv2020

Deep Learning for Feynman's Path Integral in Strong-Field Time-Dependent Dynamics

Feynman's path integral approach is to sum over all possible spatio-temporal paths to reproduce the quantum wave function and the corresponding time evolution, which has enormous potential to reveal quantum processes in classical view. However, the complete characterization of quantum wave function with infinite paths is a formidable challenge, which greatly limits the application potential, especially in the strong-field physics and attosecond science. Instead of brute-force tracking every path one by one, here we propose deep-learning-performed strong-field Feynman's formulation with pre-classification scheme which can predict directly the final results only with data of initial conditions, so as to attack unsurmountable tasks by existing strong-field methods and explore new physics. Our results build up a bridge between deep learning and strong-field physics through the Feynman's path integral, which would boost applications of deep learning to study the ultrafast time-dependent dynamics in strong-field physics and attosecond science, and shed a new light on the quantum-classical correspondence.

physics.atom-ph↗

arXiv2019

Addressing Time Bias in Bipartite Graph Ranking for Important Node Identification

The goal of the ranking problem in networks is to rank nodes from best to worst, according to a chosen criterion. In this work, we focus on ranking the nodes according to their quality. The problem of ranking the nodes in bipartite networks is valuable for many real-world applications. For instance, high-quality products can be promoted on an online shop or highly reputed restaurants attract more people on venues review platforms. However, many classical ranking algorithms share a common drawback: they tend to rank older movies higher than newer movies, though some newer movies may have a high quality. This time bias originates from the fact that older nodes in a network tend to have more connections than newer ones. In the study, we develop a ranking method using a rebalance approach to diminish the time bias of the rankings in bipartite graphs.

cs.SI↗

arXiv2019

Building Task-Oriented Visual Dialog Systems Through Alternative Optimization Between Dialog Policy and Language Generation

Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems. A common practice is to apply RL on a neural sequence-to-sequence (seq2seq) framework with the action space being the output vocabulary in the decoder. However, it is difficult to design a reward function that can achieve a balance between learning an effective policy and generating a natural dialog response. This paper proposes a novel framework that alternatively trains a RL policy for image guessing and a supervised seq2seq model to improve dialog generation quality. We evaluate our framework on the GuessWhich task and the framework achieves the state-of-the-art performance in both task completion and dialog quality.

cs.CL↗

arXiv2019

Gunrock: A Social Bot for Complex and Engaging Long Conversations

Gunrock is the winner of the 2018 Amazon Alexa Prize, as evaluated by coherence and engagement from both real users and Amazon-selected expert conversationalists. We focus on understanding complex sentences and having in-depth conversations in open domains. In this paper, we introduce some innovative system designs and related validation analysis. Overall, we found that users produce longer sentences to Gunrock, which are directly related to users' engagement (e.g., ratings, number of turns). Additionally, users' backstory queries about Gunrock are positively correlated to user satisfaction. Finally, we found dialog flows that interleave facts and personal opinions and stories lead to better user satisfaction.

cs.CL↗

arXiv2019

Learning the optimally coordinated routes from the statistical mechanics of polymers

Many major cities suffer from severe traffic congestion. Road expansion in the cites is usually infeasible, and an alternative way to alleviate traffic congestion is to coordinate the route of vehicles. Various path selection and planning algorithms are thus proposed, but most existing methods only plan paths separately and provide un-coordinated solutions. Recently, an analogy between the coordination of vehicular routes and the interaction of polymers is drawn; the spin glass theory in statistical physics is employed to optimally coordinate transportation routes. To further examine the advantages brought by path coordination, we incorporate the link congestion function developed by the Bureau of Public Roads (BPR) into the polymer routing algorithm. We then estimate in simulations the traveling time of all users saved by the polymer-BPR algorithm in randomly generated networks and real transportation networks in major cities including London, New York and Beijing. We found that a large amount of traveling time is saved in all studied networks, suggesting that the approach inspired by polymer physics is effective in minimizing the traveling time via path coordination, which is a promising tool for alleviating traffic congestions.

physics.soc-ph↗

arXiv2019

Enhancing countries' fitness with recommender systems on the international trade network

Prediction is one of the major challenges in complex systems. The prediction methods have shown to be effective predictors of the evolution of networks. These methods can help policy makers to solve practical problems successfully and make better strategy for the future. In this work, we focus on exporting countries' data of the international trading network. A recommendation system is then used to identify the products corresponding to the production capacity of each individual country, but are somehow overlook by the country. Then, we simulate the evolution of the country's fitness if it would have followed the recommendations. The result of this work is the combination combine these two methods to provide insights to countries on how to enhance the diversification of their exported products in a scientific way and improve national competitiveness significantly, especially for developing countries.

cs.SI↗

arXiv2019

Temporal similarity metrics for latent network reconstruction: The role of time-lag decay

When investigating the spreading of a piece of information or the diffusion of an innovation, we often lack information on the underlying propagation network. Reconstructing the hidden propagation paths based on the observed diffusion process is a challenging problem which has recently attracted attention from diverse research fields. To address this reconstruction problem, based on static similarity metrics commonly used in the link prediction literature, we introduce new node-node temporal similarity metrics. The new metrics take as input the time-series of multiple independent spreading processes, based on the hypothesis that two nodes are more likely to be connected if they were often infected at similar points in time. This hypothesis is implemented by introducing a time-lag function which penalizes distant infection times. We find that the choice of this time-lag strongly affects the metrics' reconstruction accuracy, depending on the network's clustering coefficient and we provide an extensive comparative analysis of static and temporal similarity metrics for network reconstruction. Our findings shed new light on the notion of similarity between pairs of nodes in complex networks.

cs.SI↗

arXiv2018

A Visual Attention Grounding Neural Model for Multimodal Machine Translation

We introduce a novel multimodal machine translation model that utilizes parallel visual and textual information. Our model jointly optimizes the learning of a shared visual-language embedding and a translator. The model leverages a visual attention grounding mechanism that links the visual semantics with the corresponding textual semantics. Our approach achieves competitive state-of-the-art results on the Multi30K and the Ambiguous COCO datasets. We also collected a new multilingual multimodal product description dataset to simulate a real-world international online shopping scenario. On this dataset, our visual attention grounding model outperforms other methods by a large margin.

cs.CL↗