Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences

Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 1951 - 1980 of 4495

Full-Text Articles in Entire DC Network

Improving Text-To-Image Synthesis Using Contrastive Learning, Hui Ye, Xiulong Yang, Martin Takáč, Raj Sunderraman, Shihao Ji Nov 2021

Improving Text-To-Image Synthesis Using Contrastive Learning, Hui Ye, Xiulong Yang, Martin Takáč, Raj Sunderraman, Shihao Ji

Machine Learning Faculty Publications

The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of words. The linguistic discrepancy between the captions of the identical image leads to the synthetic images deviating from the ground truth. To address this issue, we propose a contrastive learning approach to improve the quality and enhance the semantic consistency of synthetic images. In the pretraining stage, we utilize the contrastive learning approach to learn the consistent textual representations for …

Go to article

Multi-Modal Transformers Excel At Class-Agnostic Object Detection, Muhammad Maaz, Hanoona Bangalath Rasheed, Salman Hameed Khan, Fahad Shahbaz Khan, Rao Muhammad Anwer, Ming-Hsuan Yang Nov 2021

Multi-Modal Transformers Excel At Class-Agnostic Object Detection, Muhammad Maaz, Hanoona Bangalath Rasheed, Salman Hameed Khan, Fahad Shahbaz Khan, Rao Muhammad Anwer, Ming-Hsuan Yang

Computer Vision Faculty Publications

What constitutes an object? This has been a longstanding question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed to score objectness. However, they generally do not scale well across new domains and for unseen objects. In this paper, we advocate that existing methods lack a top-down supervision signal governed by human-understandable semantics. To bridge this gap, we explore recent Multi-modal Vision Transformers (MViT) that have been trained with aligned image-text pairs. Our extensive experiments across various domains and novel objects show the state-of-the-art performance of MViTs to localize generic objects in images. Based on …

Go to article

Provenance: An Intermediary-Free Solution For Digital Content Verification, Bilal Yousuf, M. Atif Qureshi, Brendan Spillane, Gary Munnelly, Oisin Carroll, Matthew Runswick, Kirsty Park, Eileen Culloty, Owen Conlan, Jane Suiter Nov 2021

Provenance: An Intermediary-Free Solution For Digital Content Verification, Bilal Yousuf, M. Atif Qureshi, Brendan Spillane, Gary Munnelly, Oisin Carroll, Matthew Runswick, Kirsty Park, Eileen Culloty, Owen Conlan, Jane Suiter

Articles

The threat posed by misinformation and disinformation is one of the defining challenges of the 21st century. Provenance is designed to help combat this threat by warning users when the content they are looking at may be misinformation or disinformation. It is also designed to improve media literacy among its users and ultimately reduce susceptibility to the threat among vulnerable groups within society. The Provenance browser plugin checks the content that users see on the Internet and social media and provides warnings in their browser or social media feed. Unlike similar plugins, which require human experts to provide evaluations and …

Go to article

Learning From Mistakes - A Framework For Neural Architecture Search, Bhanu Garg, Li Zhang, Pradyumna Sridhara, Ramtin Hosseini, Eric P. Xing, Pengtao Xie Nov 2021

Learning From Mistakes - A Framework For Neural Architecture Search, Bhanu Garg, Li Zhang, Pradyumna Sridhara, Ramtin Hosseini, Eric P. Xing, Pengtao Xie

Machine Learning Faculty Publications

Learning from one's mistakes is an effective human learning technique where the learners focus more on the topics where mistakes were made, so as to deepen their understanding. In this paper, we investigate if this human learning strategy can be applied in machine learning. We propose a novel machine learning method called Learning From Mistakes (LFM), wherein the learner improves its ability to learn by focusing more on the mistakes during revision. We formulate LFM as a three-stage optimization problem: 1) learner learns; 2) learner re-learns focusing on the mistakes, and; 3) learner validates its learning. We develop an efficient …

Go to article

Fighting Mass Diffusion Of Fake News On Social Media, Abdallah Musmar Nov 2021

Fighting Mass Diffusion Of Fake News On Social Media, Abdallah Musmar

USF Tampa Graduate Theses and Dissertations

Fake news has been considered one of the most challenging problems in the last few years. The effects of spreading fake news over social media platforms are widely observed across the globe as the depth and velocity of fake news reach far more than real news (Vosoughi et al., 2018). The plan for the following dissertation is to investigate the mass spread of fake news across social media and propose a framework to fight the spread of fake news by mixing preventive methods that could hinder the overall percentage of fake news sharing. We plan to create a study on …

Go to article

Topic Modeling For Multi-Aspect Listwise Comparison, Delvin Ce Zhang, Hady W. Lauw Nov 2021

Topic Modeling For Multi-Aspect Listwise Comparison, Delvin Ce Zhang, Hady W. Lauw

Research Collection School Of Computing and Information Systems

As a well-established probabilistic method, topic models seek to uncover latent semantics from plain text. In addition to having textual content, we observe that documents are usually compared in listwise rankings based on their content. For instance, world-wide countries are compared in an international ranking in terms of electricity production based on their national reports. Such document comparisons constitute additional information that reveal documents' relative similarities. Incorporating them into topic modeling could yield comparative topics that help to differentiate and rank documents. Furthermore, based on different comparison criteria, the observed document comparisons usually cover multiple aspects, each expressing a distinct …

Go to article

Does Active Service Intervention Drive More Complaints On Social Media? The Roles Of Service Quality And Awareness, Shujing Sun, Yang Gao, Huaxia Rui Nov 2021

Does Active Service Intervention Drive More Complaints On Social Media? The Roles Of Service Quality And Awareness, Shujing Sun, Yang Gao, Huaxia Rui

Research Collection School Of Computing and Information Systems

Despite many advantages of social media as a customer service channel, there is a concern that active service intervention encourages excessive service complaints. Our paper casts doubt on this misconception by examining the dynamics between social media customer complaints and brand service interventions. We find service interventions indeed cause more complaints, yet this increase is driven by service awareness rather than chronic complaining. Due to the publicity and connectivity of social media, customers learn about the new service channel by observing customer service delivery to others – a mechanism that is unique to social media customer service and does not …

Go to article

Towards Enriching Responses With Crowd-Sourced Knowledge For Task-Oriented Dialogue, Yingxu He, Lizi Liao, Zheng Zhang, Tat-Seng Chua Nov 2021

Towards Enriching Responses With Crowd-Sourced Knowledge For Task-Oriented Dialogue, Yingxu He, Lizi Liao, Zheng Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Task-oriented dialogue agents are built to assist users in completing various tasks. Generating appropriate responses for satisfactory task completion is the ultimate goal. Hence, as a convenient and straightforward way, metrics such as success rate, inform rate etc., have been widely leveraged to evaluate the generated responses. However, beyond task completion, there are several other factors that largely affect user satisfaction, which remain under-explored. In this work, we focus on analyzing different agent behavior patterns that lead to higher user satisfaction scores. Based on the findings, we design a neural response generation model EnRG. It naturally combines the power of …

Go to article

Adaptive Posterior Knowledge Selection For Improving Knowledge-Grounded Dialogue Generation, Weichao Wang, Wei Gao, Shi Feng, Ling Chen, Daling Wang Nov 2021

Adaptive Posterior Knowledge Selection For Improving Knowledge-Grounded Dialogue Generation, Weichao Wang, Wei Gao, Shi Feng, Ling Chen, Daling Wang

Research Collection School Of Computing and Information Systems

In open-domain dialogue systems, knowledge information such as unstructured persona profiles, text descriptions and structured knowledge graph can help incorporate abundant background facts for delivering more engaging and informative responses. Existing studies attempted to model a general posterior distribution over candidate knowledge by considering the entire response utterance as a whole at the beginning of decoding process for knowledge selection. However, a single smooth distribution could fail to model the variability of knowledge selection patterns over different decoding steps, and make the knowledge expression less consistent. To remedy this issue, we propose an adaptive posterior knowledge selection framework, which sequentially …

Go to article

Span-Level Emotion Cause Analysis With Neural Sequence Tagging, Xiangju Li, Wei Gao, Shi Feng, Daling Wang, Shafiq Joty Nov 2021

Span-Level Emotion Cause Analysis With Neural Sequence Tagging, Xiangju Li, Wei Gao, Shi Feng, Daling Wang, Shafiq Joty

Research Collection School Of Computing and Information Systems

This paper addresses the task of span-level emotion cause analysis (SECA). It is a finer-grained emotion cause analysis (ECA) task, which aims to identify the specific emotion cause span(s) behind certain emotions in text. In this paper, we formalize SECA as a sequence tagging task for which several variants of neural network-based sequence tagging models to extract specific emotion cause span(s) in the given context. These models combine different types of encoding and decoding approaches. Furthermore, to make our models more "emotionally sensitive'', we utilize the multi-head attention mechanism to enhance the representation of context. Experimental evaluations conducted on two …

Go to article

Automating Developer Chat Mining, Shengyi Pan, Lingfeng Bao, Xiaoxue Ren, Xin Xia, David Lo, Shanping Li Nov 2021

Automating Developer Chat Mining, Shengyi Pan, Lingfeng Bao, Xiaoxue Ren, Xin Xia, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

Online chatrooms are gaining popularity as a communication channel between widely distributed developers of Open Source Software (OSS) projects. Most discussion threads in chatrooms follow a Q&A format, with some developers (askers) raising an initial question and others (respondents) joining in to provide answers. These discussion threads are embedded with rich information that can satisfy the diverse needs of various OSS stakeholders. However, retrieving information from threads is challenging as it requires a thread-level analysis to understand the context. Moreover, the chat data is transient and unstructured, consisting of entangled informal conversations. In this paper, we address this challenge by …

Go to article

Stock Market Trend Forecasting Based On Multiple Textual Features: A Deep Learning Method, Zhenda Hu, Zhaoxia Wang, Seng-Beng Ho, Ah-Hwee Tan Nov 2021

Stock Market Trend Forecasting Based On Multiple Textual Features: A Deep Learning Method, Zhenda Hu, Zhaoxia Wang, Seng-Beng Ho, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Stock market trend forecasting is a valuable and challenging research task for both industry and academia. In order to explore the influence of stock news information on the stock market trend, a textual embedding construction method is proposed to encode multiple textual features, including topic features, sentiment features, and semantic features extracted from stock news textual content. In addition, a deep learning method is designed by using financial data and multiple textual features obtained from multiple news textual embeddings for short-term stock market trend prediction. For evaluation, extensive experiments on real stock market data are conducted. The experimental results illustrate …

Go to article

Artificial Intelligence As Augmenting Automation: Implications For Employment, F. Ted Tschang, Esteve Almirall Nov 2021

Artificial Intelligence As Augmenting Automation: Implications For Employment, F. Ted Tschang, Esteve Almirall

Research Collection Lee Kong Chian School Of Business

There has been great concern in recent years that artificial intelligence (AI) may cause widespread unemployment, but proponents say that AI augments existing jobs. Both of these positions have substance, but there is a need is to articulate the mechanisms by which AI may actually do both, and in the process, transform work and business organizations alike. We use economic studies showing past transformations automation wrought on the structure of employment and skills (such as the favouring of nonroutine skills) to articulate a ground for discussion. We then use case evidence of AI and automation to show how AI is …

Go to article

Span-Level Emotion Cause Analysis By Bert-Based Graph Attention Network, Xiangju Li, Wei Gao, Shi Feng, Daling Wang, Shafiq Joty Nov 2021

Span-Level Emotion Cause Analysis By Bert-Based Graph Attention Network, Xiangju Li, Wei Gao, Shi Feng, Daling Wang, Shafiq Joty

Research Collection School Of Computing and Information Systems

We study the task of span-level emotion cause analysis (SECA), which is focused on identifying the specific emotion cause span(s) triggering a certain emotion in the text. Compared to the popular clause-level emotion cause analysis (CECA), it is a finer-grained emotion cause analysis (ECA) task. In this paper, we design a BERT-based graph attention network for emotion cause span(s) identification. The proposed model takes advantage of the structure of BERT to capture the relationship information between emotion and text, and utilizes graph attention network to model the structure information of the text. Our SECA method can be easily used for …

Go to article

Exploiting Reasoning Chains For Multi-Hop Science Question Answering, Weiwen Xu, Yang Deng, Huihui Zhang, Deng Cai, Wai Lam Nov 2021

Exploiting Reasoning Chains For Multi-Hop Science Question Answering, Weiwen Xu, Yang Deng, Huihui Zhang, Deng Cai, Wai Lam

Research Collection School Of Computing and Information Systems

We propose a novel Chain Guided Retriever reader (CGR) framework to model the reasoning chain for multi-hop Science Question Answering. Our framework is capable of performing explainable reasoning without the need of any corpus-specific annotations, such as the ground-truth reasoning chain, or human annotated entity mentions. Specifically, we first generate reasoning chains from a semantic graph constructed by Abstract Meaning Representation of retrieved evidence facts. A Chain-aware loss, concerning both local and global chain information, is also designed to enable the generated chains to serve as distant supervision signals for training the retriever, where reinforcement learning is also adopted to …

Go to article

Building Legal Datasets, Jerrold Soh Nov 2021

Building Legal Datasets, Jerrold Soh

Research Collection Yong Pung How School Of Law

Data-centric AI calls for better, not just bigger, datasets. As data protection laws with extra-territorial reach proliferate worldwide, ensuring datasets are legal is an increasingly crucial yet overlooked component of “better”. To help dataset builders become more willing and able to navigate this complex legal space, this paper reviews key legal obligations surrounding ML datasets, examines the practical impact of data laws on ML pipelines, and offers a framework for building legal datasets.

Go to article

Wav-Bert: Cooperative Acoustic And Linguistic Representation Learning For Low-Resource Speech Recognition, Guolin Zheng, Yubei Xiao, Ke Gong, Pan Zhou, Xiaodan Liang, Liang Lin Nov 2021

Wav-Bert: Cooperative Acoustic And Linguistic Representation Learning For Low-Resource Speech Recognition, Guolin Zheng, Yubei Xiao, Ke Gong, Pan Zhou, Xiaodan Liang, Liang Lin

Research Collection School Of Computing and Information Systems

Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply cascade pre-trained acoustic and language models to learn the transfer from speech to text. However, how to solve the representation discrepancy of speech and text is unexplored, which hinders the utilization of acoustic and linguistic information. Moreover, previous works simply replace the embedding layer of the pre-trained language model with the acoustic features, which may cause the catastrophic forgetting problem. In this work, we introduce Wav-BERT, a cooperative acoustic and linguistic …

Go to article

Predicting Anti-Asian Hateful Users On Twitter During Covid-19, Jisun An, Haewoon Kwak, Claire Seungeun Lee, Bogang Jun, Yong-Yeol Ahn Nov 2021

Predicting Anti-Asian Hateful Users On Twitter During Covid-19, Jisun An, Haewoon Kwak, Claire Seungeun Lee, Bogang Jun, Yong-Yeol Ahn

Research Collection School Of Computing and Information Systems

We investigate predictors of anti-Asian hate among Twitter users throughout COVID-19. With the rise of xenophobia and polarization that has accompanied widespread social media usage in many nations, online hate has become a major social issue, attracting many researchers. Here, we apply natural language processing techniques to characterize social media users who began to post anti-Asian hate messages during COVID-19. We compare two user groups—those who posted anti-Asian slurs and those who did not—with respect to a rich set of features measured with data prior to COVID-19 and show that it is possible to predict who later publicly posted anti-Asian …

Go to article

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability, Xin Lv, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu, Yichi Zhang, Zelin Dai Nov 2021

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability, Xin Lv, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu, Yichi Zhang, Zelin Dai

Research Collection School Of Computing and Information Systems

Multi-hop reasoning has been widely studied in recent years to obtain more interpretable link prediction. However, we find in experiments that many paths given by these models are actually unreasonable, while little work has been done on interpretability evaluation for them. In this paper, we propose a unified framework to quantitatively evaluate the interpretability of multi-hop reasoning models so as to advance their development. In specific, we define three metrics, including path recall, local interpretability, and global interpretability for evaluation, and design an approximate strategy to calculate these metrics using the interpretability scores of rules. We manually annotate all possible …

Go to article

A Bert-Based Two-Stage Model For Chinese Chengyu Recommendation, Minghuan Tan, Jing Jiang, Bingtian Dai Nov 2021

A Bert-Based Two-Stage Model For Chinese Chengyu Recommendation, Minghuan Tan, Jing Jiang, Bingtian Dai

Research Collection School Of Computing and Information Systems

In Chinese, Chengyu are fixed phrases consisting of four characters. As a type of idioms, their meanings usually cannot be derived from their component characters. In this paper, we study the task of recommending a Chengyu given a textual context. Observing some of the limitations with existing work, we propose a two-stage model, where during the first stage we re-train a Chinese BERT model by masking out Chengyu from a large Chinese corpus with a wide coverage of Chengyu. During the second stage, we fine-tune the retrained, Chengyu-oriented BERT on a specific Chengyu recommendation dataset. We evaluate this method on …

Go to article

Factual Consistency Evaluation For Text Summarization Via Counterfactual Estimation, Yuexiang Xie, Fei Sun, Yang Deng, Yaliang Li, Bolin Ding Nov 2021

Factual Consistency Evaluation For Text Summarization Via Counterfactual Estimation, Yuexiang Xie, Fei Sun, Yang Deng, Yaliang Li, Bolin Ding

Research Collection School Of Computing and Information Systems

Despite significant progress has been achieved in text summarization, factual inconsistency in generated summaries still severely limits its practical applications. Among the key factors to ensure factual consistency, a reliable automatic evaluation metric is the first and the most crucial one. However, existing metrics either neglect the intrinsic cause of the factual inconsistency or rely on auxiliary tasks, leading to an unsatisfied correlation with human judgments or increasing the inconvenience of usage in practice. In light of these challenges, we propose a novel metric to evaluate the factual consistency in text summarization via counterfactual estimation, which formulates the causal relationship …

Go to article

Aspect-Based Sentiment Analysis In Question Answering Forums, Wenxuan Zhang, Yang Deng, Xin Li, Lidong Bing, Wai Lam Nov 2021

Aspect-Based Sentiment Analysis In Question Answering Forums, Wenxuan Zhang, Yang Deng, Xin Li, Lidong Bing, Wai Lam

Research Collection School Of Computing and Information Systems

Aspect-based sentiment analysis (ABSA) typically focuses on extracting aspects and predicting their sentiments on individual sentences such as customer reviews. Recently, another kind of opinion sharing platform, namely question answering (QA) forum, has received increasing popularity, which accumulates a large number of user opinions towards various aspects. This motivates us to investigate the task of ABSA on QA forums (ABSA-QA), aiming to jointly detect the discussed aspects and their sentiment polarities for a given QA pair. Unlike review sentences, a QA pair is composed of two parallel sentences, which requires interaction modeling to align the aspect mentioned in the question …

Go to article

Aspect Sentiment Quad Prediction As Paraphrase Generation, Wenxuan Zhang, Yang Deng, Xin Li, Yifei Yuan, Lidong Bing, Wai Lam Nov 2021

Aspect Sentiment Quad Prediction As Paraphrase Generation, Wenxuan Zhang, Yang Deng, Xin Li, Yifei Yuan, Lidong Bing, Wai Lam

Research Collection School Of Computing and Information Systems

Aspect-based sentiment analysis (ABSA) has been extensively studied in recent years, which typically involves four fundamental sentiment elements, including the aspect category, aspect term, opinion term, and sentiment polarity. Existing studies usually consider the detection of partial sentiment elements, instead of predicting the four elements in one shot. In this work, we introduce the Aspect Sentiment Quad Prediction (ASQP) task, aiming to jointly detect all sentiment elements in quads for a given opinionated sentence, which can reveal a more comprehensive and complete aspect-level sentiment structure. We further propose a novel Paraphrase modeling paradigm to cast the ASQP task to a …

Go to article

Fuzzy Multi Criteria Decision Making Approach For Technology Selection For Emissions Reduction From Seaborne Transportation Under Uncertainty And Vagueness, Rachid Mouaici Oct 2021

Fuzzy Multi Criteria Decision Making Approach For Technology Selection For Emissions Reduction From Seaborne Transportation Under Uncertainty And Vagueness, Rachid Mouaici

World Maritime University Dissertations

No abstract provided.

Go to article

Swift Trust And Sensemaking In Fast Response Virtual Teams, Xiaodan Yu, Yuanyanhang Shen, Deepak Khazanchi Oct 2021

Swift Trust And Sensemaking In Fast Response Virtual Teams, Xiaodan Yu, Yuanyanhang Shen, Deepak Khazanchi

Information Systems and Quantitative Analysis Faculty Publications

Fast-response virtual teams (FRVTs) have been developed as a response to emergent challenges faced by organizations that need to be addressed urgently. Even though FRVTs offer enormous potential in terms of their benefits, their success is not guaranteed. When used, the need for high performing FRVTs has become critical for organizational success. However, there is a lack of detailed understanding of how sensemaking can potentially influence FRVT performance. Drawing on social exchange theory, we identify swift trust as a potential antecedent of sensemaking. In this paper, we report the results of a study that examined the effects of swift trust …

Go to article

Noahqa: Numerical Reasoning With Interpretable Graph Question Answering Dataset, Qiyuan Zhang, Lei Wang, Sicheng Yu, Shuohang Wang, Yang Wang, Jing Jiang, Ee-Peng Lim Oct 2021

Noahqa: Numerical Reasoning With Interpretable Graph Question Answering Dataset, Qiyuan Zhang, Lei Wang, Sicheng Yu, Shuohang Wang, Yang Wang, Jing Jiang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects. First, we lack QA datasets covering complex questions that involve answers as well as the reasoning processes to get the answers. As a result, the state-of-the-art QA research on numerical reasoning still focuses on simple calculations and does not provide the mathematical expressions or evidences justifying the answers. Second, the QA community has contributed much effort to improving the interpretability of QA models. However, these models fail to explicitly show …

Go to article

Towards Enriching Responses With Crowd-Sourced Knowledge For Task-Oriented Dialogue, Yingxu He, Lizi Liao, Zheng Zhang, Tat-Seng Chua Oct 2021

Towards Enriching Responses With Crowd-Sourced Knowledge For Task-Oriented Dialogue, Yingxu He, Lizi Liao, Zheng Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Task-oriented dialogue agents are built to assist users in completing various tasks. Generating appropriate responses for satisfactory task completion is the ultimate goal. Hence, as a convenient and straightforward way, metrics such as success rate, inform rate etc., have been widely leveraged to evaluate the generated responses. However, beyond task completion, there are several other factors that largely affect user satisfaction, which remain under-explored. In this work, we focus on analyzing different agent behavior patterns that lead to higher user satisfaction scores. Based on the findings, we design a neural response generation model EnRG. It naturally combines the power of …

Go to article

A Comparative Study On Feature Extraction And Classification/Clustering Of Fake News And Conspiracy Theories From Twitter Data, Deb Shana Oct 2021

A Comparative Study On Feature Extraction And Classification/Clustering Of Fake News And Conspiracy Theories From Twitter Data, Deb Shana

Theses and Dissertations

Fake news and conspiracy theories have become largely abundant in the expanding world of social media. They predominantly affect the beliefs and thoughts of the public, resulting in chaos. They have always existed throughout the last few decades. They have been linked to prejudice, revolutions and genocide across history. They have also been known to have propelled people to reject mainstream medicines to an extent where some diseases are recurring in some parts of the world. They impose a serious impact since they are capable of spreading very fast Thus, it is very important to find suitable ways to detect …

Go to article

Disentangling Hate In Online Memes, Ka Wei, Roy Lee, Rui Cao, Ziqing Fan, Jing Jiang, Wen Haw Chong Oct 2021

Disentangling Hate In Online Memes, Ka Wei, Roy Lee, Rui Cao, Ziqing Fan, Jing Jiang, Wen Haw Chong

Research Collection School Of Computing and Information Systems

Hateful and offensive content detection has been extensively explored in a single modality such as text. However, such toxic information could also be communicated via multimodal content such as online memes. Therefore, detecting multimodal hateful content has recently garnered much attention in academic and industry research communities. This paper aims to contribute to this emerging research topic by proposing DisMultiHate, which is a novel framework that performed the classification of multimodal hateful content. Specifically, DisMultiHate is designed to disentangle target entities in multimodal memes to improve the hateful content classification and explainability. We conduct extensive experiments on two publicly available …

Go to article

Conquer: Contextual Query-Aware Ranking For Video Corpus Moment Retrieval, Zhijian Hou, Chong-Wah Ngo, W. K. Chan Oct 2021

Conquer: Contextual Query-Aware Ranking For Video Corpus Moment Retrieval, Zhijian Hou, Chong-Wah Ngo, W. K. Chan

Research Collection School Of Computing and Information Systems

This paper tackles a recently proposed Video Corpus Moment Retrieval task. This task is essential because advanced video retrieval applications should enable users to retrieve a precise moment from a large video corpus. We propose a novel CONtextual QUery-awarE Ranking (CONQUER) model for effective moment localization and ranking. CONQUER explores query context for multi-modal fusion and representation learning in two different steps. The first step derives fusion weights for the adaptive combination of multi-modal video content. The second step performs bi-directional attention to tightly couple video and query as a single joint representation for moment localization. As query context is …

Go to article

First Prev Next Last