Open Access. Powered by Scholars. Published by Universities.®
Artificial Intelligence and Robotics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Keyword
-
- Deep learning (4)
- BERT (2)
- Computer vision (2)
- Reinforcement learning (2)
- Semantics (2)
-
- Virtual reality (2)
- 360° Camera (1)
- AR/VR (1)
- Abusive Language (1)
- Action and event recognition (1)
- Address Space Layout Randomization (ASLR) (1)
- Aerospace (1)
- Allocation/Deallocation (1)
- Assessment (1)
- Augmented reality (1)
- Barcode scanning (1)
- BiLSTM (1)
- Caribbean (1)
- Categorization (1)
- Child Abuse (1)
- Codes (1)
- Computer Vision (CV) (1)
- Computing education (1)
- Conversation (1)
- Correlation (1)
- Cross-Modal Retrieval (1)
- Cross-lingual (1)
- Data models (1)
- Deep Learning (1)
- Deep learning architectures and techniques (1)
- Publication
- Publication Type
Articles 1 - 30 of 34
Full-Text Articles in Artificial Intelligence and Robotics
Movie Reviews Sentiment Analysis Using Bert, Gibson Nkhata
Movie Reviews Sentiment Analysis Using Bert, Gibson Nkhata
Graduate Theses and Dissertations
Sentiment analysis (SA) or opinion mining is analysis of emotions and opinions from texts. It is one of the active research areas in Natural Language Processing (NLP). Various approaches have been deployed in the literature to address the problem. These techniques devise complex and sophisticated frameworks in order to attain optimal accuracy with their focus on polarity classification or binary classification. In this paper, we aim to fine-tune BERT in a simple but robust approach for movie reviews sentiment analysis to provide better accuracy than state-of-the-art (SOTA) methods. We start by conducting sentiment classification for every review, followed by computing …
Prompting For Multimodal Hateful Meme Classification, Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, Jing Jiang
Prompting For Multimodal Hateful Meme Classification, Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, Jing Jiang
Research Collection School Of Computing and Information Systems
Hateful meme classification is a challenging multimodal task that requires complex reasoning and contextual background knowledge. Ideally, we could leverage an explicit external knowledge base to supplement contextual and cultural information in hateful memes. However, there is no known explicit external knowledge base that could provide such hate speech contextual information. To address this gap, we propose PromptHate, a simple yet effective prompt-based model that prompts pre-trained language models (PLMs) for hateful meme classification. Specifically, we construct simple prompts and provide a few in-context examples to exploit the implicit knowledge in the pretrained RoBERTa language model for hateful meme classification. …
Vr Computing Lab: An Immersive Classroom For Computing Learning, Shawn Pang, Kyong Jin Shim, Yi Meng Lau, Swapna Gottipati
Vr Computing Lab: An Immersive Classroom For Computing Learning, Shawn Pang, Kyong Jin Shim, Yi Meng Lau, Swapna Gottipati
Research Collection School Of Computing and Information Systems
In recent years, virtual reality (VR) is gaining popularity amongst educators and learners. If a picture is worth a thousand words, a VR session is worth a trillion words. VR technology completely immerses users with an experience that transports them into a simulated world. Universities across the United States, United Kingdom, and other countries have already started using VR for higher education in areas such as medicine, business, architecture, vocational training, social work, virtual field trips, virtual campuses, helping students with special needs, and many more. In this paper, we propose a novel VR platform learning framework which maps elements …
Enabling The Human Perception Of A Working Camera In Web Conferences Via Its Movement, Anish Shrestha
Enabling The Human Perception Of A Working Camera In Web Conferences Via Its Movement, Anish Shrestha
LSU Master's Theses
In recent years, video conferencing has seen a significant increase in its usage due to the COVID-19 pandemic. When casting user’s video to other participants, the videoconference applications (e.g. Zoom, FaceTime, Skype, etc.) mainly leverage 1) webcam’s LED-light indicator, 2) user’s video feedback in the software and 3) the software’s video on/off icons to remind the user whether the camera is being used. However, these methods all impose the responsibility on the user itself to check the camera status, and there have been numerous cases reported when users expose their privacy inadvertently due to not realizing that their camera is …
Controllable Neural Synthesis For Natural Images And Vector Art, Difan Liu
Controllable Neural Synthesis For Natural Images And Vector Art, Difan Liu
Doctoral Dissertations
Neural image synthesis approaches have become increasingly popular over the last years due to their ability to generate photorealistic images useful for several applications, such as digital entertainment, mixed reality, synthetic dataset creation, computer art, to name a few. Despite the progress over the last years, current approaches lack two important aspects: (a) they often fail to capture long-range interactions in the image, and as a result, they fail to generate scenes with complex dependencies between their different objects or parts. (b) they often ignore the underlying 3D geometry of the shape/scene in the image, and as a result, they …
Interactive Video Corpus Moment Retrieval Using Reinforcement Learning, Zhixin Ma, Chong-Wah Ngo
Interactive Video Corpus Moment Retrieval Using Reinforcement Learning, Zhixin Ma, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Known-item video search is effective with human-in-the-loop to interactively investigate the search result and refine the initial query. Nevertheless, when the first few pages of results are swamped with visually similar items, or the search target is hidden deep in the ranked list, finding the know-item target usually requires a long duration of browsing and result inspection. This paper tackles the problem by reinforcement learning, aiming to reach a search target within a few rounds of interaction by long-term learning from user feedbacks. Specifically, the system interactively plans for navigation path based on feedback and recommends a potential target that …
Long-Term Leap Attention, Short-Term Periodic Shift For Video Classification, Hao Zhang, Lechao Cheng, Yanbin Hao, Chong-Wah Ngo
Long-Term Leap Attention, Short-Term Periodic Shift For Video Classification, Hao Zhang, Lechao Cheng, Yanbin Hao, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes �� times longer sequence than the latter under the current attention of quadratic complexity (�� 2�� 2 ). The existing works treat the temporal axis as a simple extension of spatial axes, focusing on shortening the spatio-temporal sequence by either generic pooling or local windowing without utilizing temporal redundancy. However, videos naturally contain redundant information between neighboring frames; thereby, we could potentially suppress attention on visually similar frames in a dilated manner. Based on this hypothesis, we propose the LAPS, a long-term “Leap …
Pixel-Wise Energy-Biased Abstention Learning For Anomaly Segmentation On Complex Urban Driving Scenes, Yu Tian, Yuyuan Liu, Guansong Pang, Fengbei Liu, Yuanhong Chen, Gustavo Carneiro
Pixel-Wise Energy-Biased Abstention Learning For Anomaly Segmentation On Complex Urban Driving Scenes, Yu Tian, Yuyuan Liu, Guansong Pang, Fengbei Liu, Yuanhong Chen, Gustavo Carneiro
Research Collection School Of Computing and Information Systems
State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external reconstruction models. However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems. In this paper, we propose a new anomaly segmentation method, named pixel-wise energy-biased abstention learning (PEBAL), that explores pixel-wise abstention learning (AL) with a model that learns an adaptive pixel-level anomaly class, and an energy-based model (EBM) that learns inlier pixel distribution. More specifically, PEBAL is …
Wave-Vit: Unifying Wavelet And Transformers For Visual Representation Learning, Ting Yao, Yingwei Pan, Yehao Li, Chong-Wah Ngo, Tao Mei
Wave-Vit: Unifying Wavelet And Transformers For Visual Representation Learning, Ting Yao, Yingwei Pan, Yehao Li, Chong-Wah Ngo, Tao Mei
Research Collection School Of Computing and Information Systems
Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly employ down-sampling operations (e.g., average pooling) over keys/values to dramatically reduce the computational cost. In this work, we argue that such over-aggressive down-sampling design is not invertible and inevitably causes information dropping especially for high-frequency components in objects (e.g., texture details). Motivated by the wavelet theory, we construct a new Wavelet Vision Transformer (Wave-ViT) that formulates the invertible down-sampling with wavelet transforms and self-attention learning in a unified way. …
Cvfnet: Real-Time 3d Object Detection By Learning Cross View Features, Jiaqi Gu, Zhiyu Xiang, Pan Zhao, Tingming Bai, Lingxuan Wang, Xijun Zhao, Zhiyuan Zhang
Cvfnet: Real-Time 3d Object Detection By Learning Cross View Features, Jiaqi Gu, Zhiyu Xiang, Pan Zhao, Tingming Bai, Lingxuan Wang, Xijun Zhao, Zhiyuan Zhang
Research Collection School Of Computing and Information Systems
In recent years 3D object detection from LiDAR point clouds has made great progress thanks to the development of deep learning technologies. Although voxel or point based methods are popular in 3D object detection, they usually involve time-consuming operations such as 3D convolutions on voxels or ball query among points, making the resulting network inappropriate for time critical applications. On the other hand, 2D view-based methods feature high computing efficiency while usually obtaining inferior performance than the voxel or point based methods. In this work, we present a real-time view-based single stage 3D object detector, namely CVFNet to fulfill this …
Dynamic Temporal Filtering In Video Models, Fuchen Long, Zhaofan Qiu, Yingwei Pan, Ting Yao, Chong-Wah Ngo, Tao Mei
Dynamic Temporal Filtering In Video Models, Fuchen Long, Zhaofan Qiu, Yingwei Pan, Ting Yao, Chong-Wah Ngo, Tao Mei
Research Collection School Of Computing and Information Systems
Video temporal dynamics is conventionally modeled with 3D spatial-temporal kernel or its factorized version comprised of 2D spatial kernel and 1D temporal kernel. The modeling power, nevertheless, is limited by the fixed window size and static weights of a kernel along the temporal dimension. The pre-determined kernel size severely limits the temporal receptive fields and the fixed weights treat each spatial location across frames equally, resulting in sub-optimal solution for longrange temporal modeling in natural scenes. In this paper, we present a new recipe of temporal feature learning, namely Dynamic Temporal Filter (DTF), that novelly performs spatial-aware temporal modeling in …
Fair, Equitable, And Just: A Socio-Technical Approach To Online Safety, Daricia Wilkinson
Fair, Equitable, And Just: A Socio-Technical Approach To Online Safety, Daricia Wilkinson
All Dissertations
Socio-technical systems have been revolutionary in reshaping how people maintain relationships, learn about new opportunities, engage in meaningful discourse, and even express grief and frustrations. At the same time, these systems have been central in the proliferation of harmful behaviors online as internet users are confronted with serious and pervasive threats at alarming rates. Although researchers and companies have attempted to develop tools to mitigate threats, the perception of dominant (often Western) frameworks as the standard for the implementation of safety mechanisms fails to account for imbalances, inequalities, and injustices in non-Western civilizations like the Caribbean. Therefore, in this dissertation …
Towards Improving System Performance In Large Scale Multi-Agent Systems With Selfish Agents, Rajiv Ranjan Kumar
Towards Improving System Performance In Large Scale Multi-Agent Systems With Selfish Agents, Rajiv Ranjan Kumar
Dissertations and Theses Collection (Open Access)
Intelligent agents are becoming increasingly prevalent in a wide variety of domains including but not limited to transportation, safety and security. To better utilize the intelligence, there has been increasing focus on frameworks and methods for coordinating these intelligent agents. This thesis is specifically targeted at providing solution approaches for improving large scale multi-agent systems with selfish intelligent agents. In such systems, the performance of an agent depends on not just his/her own efforts, but also on other agent’s decisions. The complexity of interactions among multiple agents, coupled with the large scale nature of the problem domains and the uncertainties …
Analysis Of Digital Image Segmentation Algorithms, Khalilov Sirojiddin
Analysis Of Digital Image Segmentation Algorithms, Khalilov Sirojiddin
Karakalpak Scientific Journal
Ushbu maqolada zamonaviy axborot-kommunikatsiya texnologiyalaridan foydalanishni kengaytirish maqsadida raqamli tasvirni qayta ishlash usullari va algoritmlari tahlil qilinadi. Maqolada, shuningdek, raqamli tasvirni qayta ishlash, tasvirni segmentatsiyalash usullari, WaterShed, MeanShift, FloodFill, GrabCut algoritmlarining afzalliklari va kamchiliklari o'rganiladi.
Group Contextualization For Video Recognition, Yanbin Hao, Hao Zhang, Chong-Wah Ngo, Xiangnan He
Group Contextualization For Video Recognition, Yanbin Hao, Hao Zhang, Chong-Wah Ngo, Xiangnan He
Research Collection School Of Computing and Information Systems
Learning discriminative representation from the complex spatio-temporal dynamic space is essential for video recognition. On top of those stylized spatio-temporal computational units, further refining the learnt feature with axial contexts is demonstrated to be promising in achieving this goal. However, previous works generally focus on utilizing a single kind of contexts to calibrate entire feature channels and could hardly apply to deal with diverse video activities. The problem can be tackled by using pair-wise spatio-temporal attentions to recompute feature response with cross-axis contexts at the expense of heavy computations. In this paper, we propose an efficient feature refinement method that …
Reinforcement Learning-Based Interactive Video Search, Zhixin Ma, Jiaxin Wu, Zhijian Hou, Chong-Wah Ngo
Reinforcement Learning-Based Interactive Video Search, Zhixin Ma, Jiaxin Wu, Zhijian Hou, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Despite the rapid progress in text-to-video search due to the advancement of cross-modal representation learning, the existing techniques still fall short in helping users to rapidly identify the search targets. Particularly, in the situation that a system suggests a long list of similar candidates, the user needs to painstakingly inspect every search result. The experience is frustrated with repeated watching of similar clips, and more frustratingly, the search targets may be overlooked due to mental tiredness. This paper explores reinforcement learning-based (RL) searching to relieve the user from the burden of brute force inspection. Specifically, the system maintains a graph …
Mlp-3d: A Mlp-Like 3d Architecture With Grouped Time Mixing, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei
Mlp-3d: A Mlp-Like 3d Architecture With Grouped Time Mixing, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei
Research Collection School Of Computing and Information Systems
Convolutional Neural Networks (CNNs) have been re-garded as the go-to models for visual recognition. More re-cently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more popular. Nevertheless, it is not trivial when utilizing these newly-minted networks for video recognition due to the large variations and complexities in video data. In this paper, we present MLP-3D networks, a novel MLP-like 3D architecture for video recognition. Specifically, the architecture consists of MLP-3D blocks, where each block contains one MLP applied across tokens (i.e., token-mixing MLP) and one MLP applied independently to each token (i.e., channel MLP). …
Multimodal Zero-Shot Hateful Meme Detection, Jiawen Zhu, Roy Ka-Wei Lee, Wen Haw Chong
Multimodal Zero-Shot Hateful Meme Detection, Jiawen Zhu, Roy Ka-Wei Lee, Wen Haw Chong
Research Collection School Of Computing and Information Systems
Facebook has recently launched the hateful meme detection challenge, which garnered much attention in academic and industry research communities. Researchers have proposed multimodal deep learning classification methods to perform hateful meme detection. While the proposed methods have yielded promising results, these classification methods are mostly supervised and heavily rely on labeled data that are not always available in the real-world setting. Therefore, this paper explores and aims to perform hateful meme detection in a zero-shot setting. Working towards this goal, we propose Target-Aware Multimodal Enhancement (TAME), which is a novel deep generative framework that can improve existing hateful meme classification …
Cross-Lingual Adaptation For Recipe Retrieval With Mixup, Bin Zhu, Chong-Wah Ngo, Jingjing Chen, Wing-Kwong Chan
Cross-Lingual Adaptation For Recipe Retrieval With Mixup, Bin Zhu, Chong-Wah Ngo, Jingjing Chen, Wing-Kwong Chan
Research Collection School Of Computing and Information Systems
Cross-modal recipe retrieval has attracted research attention in recent years, thanks to the availability of large-scale paired data for training. Nevertheless, obtaining adequate recipe-image pairs covering the majority of cuisines for supervised learning is difficult if not impossible. By transferring knowledge learnt from a data-rich cuisine to a data-scarce cuisine, domain adaptation sheds light on this practical problem. Nevertheless, existing works assume recipes in source and target domains are mostly originated from the same cuisine and written in the same language. This paper studies unsupervised domain adaptation for image-to-recipe retrieval, where recipes in source and target domains are in different …
High-Resolution Face Swapping Via Latent Semantics Disentanglement, Yangyang Xu, Bailin Deng, Junle Wang, Yanqing Jing, Jia Pan, Shengfeng He
High-Resolution Face Swapping Via Latent Semantics Disentanglement, Yangyang Xu, Bailin Deng, Junle Wang, Yanqing Jing, Jia Pan, Shengfeng He
Research Collection School Of Computing and Information Systems
We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator, deriving structure at-tributes from the shallow layers and appearance attributes from the deeper ones. Identity and pose information within the structure attributes are further separated by introducing a landmark-driven structure transfer latent direction. The disentangled latent code produces rich generative features that incorporate feature blending …
Gauging The State-Of-The-Art For Foresight Weight Pruning On Neural Networks, Noah James
Gauging The State-Of-The-Art For Foresight Weight Pruning On Neural Networks, Noah James
Computer Science and Computer Engineering Undergraduate Honors Theses
The state-of-the-art for pruning neural networks is ambiguous due to poor experimental practices in the field. Newly developed approaches rarely compare to each other, and when they do, their comparisons are lackluster or contain errors. In the interest of stabilizing the field of pruning, this paper initiates a dive into reproducing prominent pruning algorithms across several architectures and datasets. As a first step towards this goal, this paper shows results for foresight weight pruning across 6 baseline pruning strategies, 5 modern pruning strategies, random pruning, and one legacy method (Optimal Brain Damage). All strategies are evaluated on 3 different architectures …
Analysis Of Gpu Memory Vulnerabilities, Jarrett Hoover
Analysis Of Gpu Memory Vulnerabilities, Jarrett Hoover
Computer Science and Computer Engineering Undergraduate Honors Theses
Graphics processing units (GPUs) have become a widely used technology for various purposes. While their intended use is accelerating graphics rendering, their parallel computing capabilities have expanded their use into other areas. They are used in computer gaming, deep learning for artificial intelligence and mining cryptocurrencies. Their rise in popularity led to research involving several security aspects, including this paper’s focus, memory vulnerabilities. Research documented many vulnerabilities, including GPUs not implementing address space layout randomization, not zeroing out memory after deallocation, and not initializing newly allocated memory. These vulnerabilities can lead to a victim’s sensitive data being leaked to an …
Using A Bert-Based Ensemble Network For Abusive Language Detection, Noah Ballinger
Using A Bert-Based Ensemble Network For Abusive Language Detection, Noah Ballinger
Computer Science and Computer Engineering Undergraduate Honors Theses
Over the past two decades, online discussion has skyrocketed in scope and scale. However, so has the amount of toxicity and offensive posts on social media and other discussion sites. Despite this rise in prevalence, the ability to automatically moderate online discussion platforms has seen minimal development. Recently, though, as the capabilities of artificial intelligence (AI) continue to improve, the potential of AI-based detection of harmful internet content has become a real possibility. In the past couple years, there has been a surge in performance on tasks in the field of natural language processing, mainly due to the development of …
Designing A Digital Interactive Emotion Measure (Diem) For Digital Media: Theoretical Foundations And Validation Protocols, Celeste Sangiorgio, Cassandra Berbary, Cory Crane, Caroline Easton
Designing A Digital Interactive Emotion Measure (Diem) For Digital Media: Theoretical Foundations And Validation Protocols, Celeste Sangiorgio, Cassandra Berbary, Cory Crane, Caroline Easton
Frameless
Awareness of emotions is often a treatment target in psychotherapy, but it is difficult to assess emotions due to ambiguity in measurement or scale design. Lack of clarity in scale design may increase risk that participant interpretations of scale items may not align with emotion constructs those scales were designed to capture. Furthermore, emphasis on verbal or written cues leads to low scientific representation of patients who cannot read emotion scales (e.g., low literacy). Touch-screen applications provide a unique opportunity to create a visual emotion measure which has low barriers but can be used to assess a high level of …
Novel 360-Degree Camera, Ian Gauger, Andrew Kurtz, Zakariya Niazi
Novel 360-Degree Camera, Ian Gauger, Andrew Kurtz, Zakariya Niazi
Frameless
Circle Optics is developing novel technology for low-parallax, real time, panoramic image capture using an integrated array of multiple adjacent polygonal-edged cameras. This technology can be optimized and deployed for a variety of markets, including cinematic VR. Circle Optics’ existing prototype, Hydra Alpha, will be demonstrated.
Warehouse And Logistics: Smart Picking With Vuzix Smart Glasses, Elise Hemink
Warehouse And Logistics: Smart Picking With Vuzix Smart Glasses, Elise Hemink
Frameless
Vuzix is an industry leader in augmented reality (AR) technology. We provide innovative products to an array of industries, a few being defense, security, enterprise, and consumers. Our AR technology provides a perfect balance of engagement in the digital and real worlds thanks to their innovative optics, AI apps and 5G capability.
Creating A Virtual Reality Experience In Service To A Non-Profit Agency, Frank Deese, Susan Lakin, Isabelle Anderson
Creating A Virtual Reality Experience In Service To A Non-Profit Agency, Frank Deese, Susan Lakin, Isabelle Anderson
Frameless
In the summer of 2018, RIT Professors Susan Lakin and Frank Deese discussed with the principal officers of the Society for the Protection and Care of Children (SPCC) in Rochester how the new technology of Virtual Reality might be used to not only impart information to viewers, but generate empathy for those receiving services from the organization as well as those performing those services. Their ultimate goal was to create an experience that could be viewed with VR headsets at fundraising events and on a website using low-cost Google Cardboard.
Comai: Enabling Lightweight, Collaborative Intelligence By Retrofitting Vision Dnns, Kasthuri Jayarajah, Dhanuja Wanniarachchige, Tarek Abdelzaher, Archan Misra
Comai: Enabling Lightweight, Collaborative Intelligence By Retrofitting Vision Dnns, Kasthuri Jayarajah, Dhanuja Wanniarachchige, Tarek Abdelzaher, Archan Misra
Research Collection School Of Computing and Information Systems
While Deep Neural Network (DNN) models have transformed machine vision capabilities, their extremely high computational complexity and model sizes present a formidable deployment roadblock for AIoT applications. We show that the complexity-vs-accuracy-vs-communication tradeoffs for such DNN models can be significantly addressed via a novel, lightweight form of “collaborative machine intelligence” that requires only runtime changes to the inference process. In our proposed approach, called ComAI, the DNN pipelines of different vision sensors share intermediate processing state with one another, effectively providing hints about objects located within their mutually-overlapping Field-of-Views (FoVs). CoMAI uses two novel techniques: (a) a secondary shallow ML …
Deconfounded Visual Grounding, Jianqiang Huang, Yu Qin, Jiaxin Qi, Qianru Sun, Hanwang Zhang
Deconfounded Visual Grounding, Jianqiang Huang, Yu Qin, Jiaxin Qi, Qianru Sun, Hanwang Zhang
Research Collection School Of Computing and Information Systems
We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example, the grounding process is usually a trivial languagelocation association without visual reasoning, e.g., grounding any language query containing sheep to the nearly central regions, due to that most queries about sheep have groundtruth locations at the image center. First, we frame the visual grounding pipeline into a causal graph, which shows the causalities among image, query, target location and underlying confounder. Through the causal graph, we know how to break the …
Debiasing Nlu Models Via Causal Intervention And Counterfactual Reasoning, Bing Tian, Yixin Cao, Yong Zhang, Chunxiao Xing
Debiasing Nlu Models Via Causal Intervention And Counterfactual Reasoning, Bing Tian, Yixin Cao, Yong Zhang, Chunxiao Xing
Research Collection School Of Computing and Information Systems
Recent studies have shown that strong Natural Language Understanding (NLU) models are prone to relying on annotation biases of the datasets as a shortcut, which goes against the underlying mechanisms of the task of interest. To reduce such biases, several recent works introduce debiasing methods to regularize the training process of targeted NLU models. In this paper, we provide a new perspective with causal inference to fnd out the bias. On the one hand, we show that there is an unobserved confounder for the natural language utterances and their respective classes, leading to spurious correlations from training data. To remove …