Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- Singapore Management University (1112)
- TÜBİTAK (199)
- Wright State University (191)
- Technological University Dublin (182)
- Old Dominion University (126)
-
- Missouri University of Science and Technology (112)
- San Jose State University (111)
- City University of New York (CUNY) (93)
- Neutrosophic Systems with Applications (92)
- MBZUAI (70)
- Dartmouth College (67)
- Brigham Young University (65)
- University of Texas at El Paso (63)
- Chulalongkorn University (62)
- Zayed University (58)
- University of Nebraska - Lincoln (56)
- Edith Cowan University (50)
- Kennesaw State University (49)
- Boise State University (48)
- New Jersey Institute of Technology (44)
- California Polytechnic State University, San Luis Obispo (43)
- Chapman University (42)
- Embry-Riddle Aeronautical University (42)
- MMU Press (41)
- Purdue University (41)
- University of Nebraska at Omaha (40)
- University of Arkansas, Fayetteville (39)
- Montclair State University (37)
- University of Central Florida (36)
- University of South Florida (36)
- Keyword
-
- Machine learning (186)
- Natural language processing (184)
- Artificial intelligence (141)
- Natural Language Processing (134)
- Machine Learning (127)
-
- Deep learning (119)
- Artificial Intelligence (95)
- Large language models (84)
- Computer Science (80)
- Social media (80)
- Twitter (64)
- NLP (62)
- Deep Learning (61)
- Sentiment analysis (59)
- Large Language Models (56)
- Computational linguistics (53)
- Department of Computer Science and Engineering (53)
- Text mining (51)
- Neural networks (48)
- Generative AI (46)
- Data mining (44)
- AI (43)
- Computer science (40)
- Classification (37)
- Information retrieval (36)
- Social Media (36)
- Fuzzy logic (35)
- Semantics (34)
- Sentiment Analysis (34)
- LLM (32)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (1036)
- Turkish Journal of Electrical Engineering and Computer Sciences (199)
- Theses and Dissertations (162)
- Master's Projects (99)
- Conference papers (93)
-
- Neutrosophic Systems with Applications (92)
- Kno.e.sis Publications (84)
- Dissertations (70)
- Computer Science Faculty Research & Creative Works (66)
- Chulalongkorn University Theses and Dissertations (Chula ETD) (62)
- Browse all Theses and Dissertations (61)
- All Works (58)
- Computer Science Faculty Publications (58)
- Faculty Publications (49)
- Computer Science Faculty Publications and Presentations (45)
- Publications and Research (44)
- Journal of Informatics and Web Engineering (41)
- Articles (40)
- Electronic Theses and Dissertations (39)
- Computer Science and Engineering Faculty Publications (38)
- Natural Language Processing Faculty Publications (38)
- Departmental Technical Reports (CS) (36)
- Dissertations and Theses Collection (Open Access) (35)
- USF Tampa Graduate Theses and Dissertations (34)
- Computer Science: Faculty Publications (33)
- Dissertations, Theses, and Capstone Projects (32)
- Theses (31)
- CCAC Theses and Dissertations (30)
- Faculty Scholarship (28)
- Masters Theses (26)
- Publication Type
- File Type
Articles 2281 - 2310 of 4507
Full-Text Articles in Entire DC Network
Designing Leakage-Resilient Password Entry On Head-Mounted Smart Wearable Glass Devices, Yan Li, Yao Cheng, Wenzhi Meng, Yingjiu Li, Robert H. Deng
Designing Leakage-Resilient Password Entry On Head-Mounted Smart Wearable Glass Devices, Yan Li, Yao Cheng, Wenzhi Meng, Yingjiu Li, Robert H. Deng
Research Collection School Of Computing and Information Systems
With the boom of Augmented Reality (AR) and Virtual Reality (VR) applications, head-mounted smart wearable glass devices are becoming popular to help users access various services like E-mail freely. However, most existing password entry schemes on smart glasses rely on additional computers or mobile devices connected to smart glasses, which require users to switch between different systems and devices. This may greatly lower the practicability and usability of smart glasses. In this paper, we focus on this challenge and design three practical anti-eavesdropping password entry schemes on stand-alone smart glasses, named gTapper, gRotator and gTalker. The main idea is to …
Empirical Analysis Of Cbow And Skip Gram Nlp Models, Tejas Menon
Empirical Analysis Of Cbow And Skip Gram Nlp Models, Tejas Menon
University Honors Theses
CBOW and Skip Gram are two NLP techniques to produce word embedding models that are accurate and performant. They were invented in the seminal paper by T. Mikolov et al. and have since observed optimizations such as negative sampling and subsampling. This paper implements a fully-optimized version of these models using Py-Torch and runs them through a toy sentiment/subject analysis. It is weakly observed that different corpus types affect the skew of word embeddings such that fictional corpus are better suited for sentiment analysis and non-fictional for subject analysis.
Automatic Keyphrase Extraction From Russian-Language Scholarly Papers In Computational Linguistics, Yves Wienecke
Automatic Keyphrase Extraction From Russian-Language Scholarly Papers In Computational Linguistics, Yves Wienecke
University Honors Theses
The automatic extraction of keyphrases from scholarly papers is a necessary step for many Natural Language Processing (NLP) tasks, including text retrieval, machine translation, and text summarization. However, due to the different grammatical and semantic intricacies of languages, this is a highly language-dependent task. Many free and open source implementations of state-of-the-art keyphrase extraction techniques exist, but they are not adapted for processing Russian text. Furthermore, the multi-linguistic character of scholarly papers in the field of Russian computational linguistics and NLP introduces additional complexity to keyphrase extraction. This paper describes a free and open source program as a proof of …
Graph-To-Tree Learning For Solving Math Word Problems, Jipeng Zhang, Lei Wang, Roy Ka-Wei Lee, Yi Bin, Yan Wang, Jie Shao, Ee-Peng Lim
Graph-To-Tree Learning For Solving Math Word Problems, Jipeng Zhang, Lei Wang, Roy Ka-Wei Lee, Yi Bin, Yan Wang, Jie Shao, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities well. This results in poor quantity representations and incorrect solution expressions. In this paper, we propose Graph2Tree, a novel deep learning architecture that combines the merits of the graph-based encoder and tree-based decoder to generate better solution expressions. Included in our Graph2Tree framework are two graphs, namely the Quantity Cell Graph and Quantity Comparison Graph, which are designed to address limitations of existing methods by …
Expertise Style Transfer: A New Task Towards Better Communication Between Experts And Laymen, Yixin Cao, Ruihao Shui, Liangming Pan, Min-Yen Kan, Zhiyuan Lu, Tat-Seng Chua
Expertise Style Transfer: A New Task Towards Better Communication Between Experts And Laymen, Yixin Cao, Ruihao Shui, Liangming Pan, Min-Yen Kan, Zhiyuan Lu, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
The curse of knowledge can impede communication between experts and laymen. We propose a new task of expertise style transfer and contribute a manually annotated dataset with the goal of alleviating such cognitive biases. Solving this task not only simplifies the professional language, but also improves the accuracy and expertise level of laymen descriptions using simple words. This is a challenging task, unaddressed in previous work, as it requires the models to have expert intelligence in order to modify text with a deep understanding of domain knowledge and structures. We establish the benchmark performance of five state-of-the-art models for style …
Tree-Augmented Cross-Modal Encoding For Complex-Query Video Retrieval, Xun Yang, Jianfeng Dong, Yixin Cao, Xun Wang, Meng Wang, Tat-Seng Chua
Tree-Augmented Cross-Modal Encoding For Complex-Query Video Retrieval, Xun Yang, Jianfeng Dong, Yixin Cao, Xun Wang, Meng Wang, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
The rapid growth of user-generated videos on the Internet has intensified the need for text-based video retrieval systems. Traditional methods mainly favor the concept-based paradigm on retrieval with simple queries, which are usually ineffective for complex queries that carry far more complex semantics. Recently, embedding-based paradigm has emerged as a popular approach. It aims to map the queries and videos into a shared embedding space where semantically-similar texts and videos are much closer to each other. Despite its simplicity, it forgoes the exploitation of the syntactic structure of text queries, making it suboptimal to model the complex queries. To facilitate …
Enhancing The Performance Of Ir-Based Traceability Recovery Of Requirement Artifacts Using Noun Phrases, Dafaalla Abdelrahman Mashahi Khalafalla
Enhancing The Performance Of Ir-Based Traceability Recovery Of Requirement Artifacts Using Noun Phrases, Dafaalla Abdelrahman Mashahi Khalafalla
Student Works (2020-2029)
Requirement traceability can be considered as a measure of software quality to help achieve validation, verification, and reusability. Neglecting traceability leads to less maintainable software. Creating traceability links after-the-fact, known as traceability recovery, is a tedious and time-consuming process when it is done manually. Therefore, information retrieval (IR) methods have been used to automatically identify traceability links between the artifacts. However, as a result of limitations of the software engineer and the IR techniques, the performance of the IR methods is negatively affected. There is no IR method that is able to recover traceability links between artifacts with high precision …
What Was Written Vs. Who Read It: News Media Profiling Using Text Analysis And Social Media Context, Ramy Baly, Georgi Karadzhov, Jisun An, Haewoon Kwak, Yoan Dinkov, Ahmed Ali, James Glass, Preslav. Nakov
What Was Written Vs. Who Read It: News Media Profiling Using Text Analysis And Social Media Context, Ramy Baly, Georgi Karadzhov, Jisun An, Haewoon Kwak, Yoan Dinkov, Ahmed Ali, James Glass, Preslav. Nakov
Research Collection School Of Computing and Information Systems
Predicting the political bias and the factuality of reporting of entire news outlets are critical elements of media profiling, which is an understudied but an increasingly important research direction. The present level of proliferation of fake, biased, and propagandistic content online has made it impossible to fact-check every single suspicious claim, either manually or automatically. Thus, it has been proposed to profile entire news outlets and to look for those that are likely to publish fake or biased content. This makes it possible to detect likely “fake news” the moment they are published, by simply checking the reliability of their …
Video-Grounded Dialogues With Pretrained Generation Language Models, Hung Le, Steven C. H. Hoi
Video-Grounded Dialogues With Pretrained Generation Language Models, Hung Le, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
Pre-trained language models have shown remarkable success in improving various downstream NLP tasks due to their ability to capture dependencies in textual data and generate natural responses. In this paper, we leverage the power of pre-trained language models for improving video-grounded dialogue, which is very challenging and involves complex features of different dynamics: (1) Video features which can extend across both spatial and temporal dimensions; and (2) Dialogue features which involve semantic dependencies over multiple dialogue turns. We propose a framework by extending GPT-2 models to tackle these challenges by formulating video-grounded dialogue tasks as a sequence-to-sequence task, combining both …
Improving Event Detection Via Open-Domain Event Trigger Knowledge, Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li, Jun Xie
Improving Event Detection Via Open-Domain Event Trigger Knowledge, Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li, Jun Xie
Research Collection School Of Computing and Information Systems
Event Detection (ED) is a fundamental task in automatically structuring texts. Due to the small scale of training data, previous methods perform poorly on unseen/sparsely labeled trigger words and are prone to overfitting densely labeled trigger words. To address the issue, we propose a novel Enrichment Knowledge Distillation (EKD) model to leverage external open-domain trigger knowledge to reduce the in-built biases to frequent trigger words in annotations. Experiments on benchmark ACE2005 show that our model outperforms nine strong baselines, is especially effective for unseen/sparsely labeled trigger words. The source code is released on https://github.com/shuaiwa16/ekd.git.
A Systematic Media Frame Analysis Of 1.5 Million New York Times Articles From 2000 To 2017, Haewoon Kwak, Jisun An
A Systematic Media Frame Analysis Of 1.5 Million New York Times Articles From 2000 To 2017, Haewoon Kwak, Jisun An
Research Collection School Of Computing and Information Systems
Framing is an indispensable narrative device for news media because even the same facts may lead to conflicting understandings if deliberate framing is employed. Therefore, identifying media framing is a crucial step to understanding how news media influence the public. Framing is, however, difficult to operationalize and detect, and thus traditional media framing studies had to rely on manual annotation, which is challenging to scale up to massive news datasets. Here, by developing a media frame classifier that achieves state-of-the-art performance, we systematically analyze the media frames of 1.5 million New York Times articles published from 2000 to 2017. By …
Interactive Entity Linking Using Entity-Word Representations, Pei Chi Lo, Ee-Peng Lim
Interactive Entity Linking Using Entity-Word Representations, Pei Chi Lo, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
To leverage on entity and word semantics in entity linking, embedding models have been developed to represent entities, words and their context such that candidate entities for each mention can be determined and ranked accurately using their embeddings. To leverage on entity and word semantics in entity linking, embedding models have been developed to represent entities, words and their context such that candidate entities for each mention can be determined and ranked accurately using their embeddings. In this paper, we leverage on human intelligence for embedding-based interactive entity linking. We adopt an active learning approach to select mentions for human …
Query Graph Generation For Answering Multi-Hop Complex Questions From Knowledge Bases, Yunshi Lan, Jing Jiang
Query Graph Generation For Answering Multi-Hop Complex Questions From Knowledge Bases, Yunshi Lan, Jing Jiang
Research Collection School Of Computing and Information Systems
Previous work on answering complex questions from knowledge bases usually separately addresses two types of complexity: questions with constraints and questions with multiple hops of relations. In this paper, we handle both types of complexity at the same time. Motivated by the observation that early incorporation of constraints into query graphs can more effectively prune the search space, we propose a modified staged query graph generation method with more flexible ways to generate query graphs. Our experiments clearly show that our method achieves the state of the art on three benchmark KBQA datasets.
Improving Multimodal Named Entity Recognition Via Entity Span Detection With Unified Multimodal Transformer, Jianfei Yu, Jing Jiang, Li Yang, Rui Xia
Improving Multimodal Named Entity Recognition Via Entity Span Detection With Unified Multimodal Transformer, Jianfei Yu, Jing Jiang, Li Yang, Rui Xia
Research Collection School Of Computing and Information Systems
In this paper, we study Multimodal Named Entity Recognition (MNER) for social media posts. Existing approaches for MNER mainly suffer from two drawbacks: (1) despite generating word-aware visual representations, their word representations are insensitive to the visual context; (2) most of them ignore the bias brought by the visual context. To tackle the first issue, we propose a multimodal interaction module to obtain both image-aware word representations and word-aware visual representations. To alleviate the visual bias, we further propose to leverage purely text-based entity span detection as an auxiliary module, and design a Unified Multimodal Transformer to guide the final …
Dynamic Trajectory Generation And A Robust Controller To Intercept A Moving Ball In A Game Setting, Ravi Prakash, Laxmidhar Behera, Santhakumar Mohan, Sarangapani Jagannathan
Dynamic Trajectory Generation And A Robust Controller To Intercept A Moving Ball In A Game Setting, Ravi Prakash, Laxmidhar Behera, Santhakumar Mohan, Sarangapani Jagannathan
Electrical and Computer Engineering Faculty Research & Creative Works
Complex and interactive robot manipulation skills, such as playing a game of table tennis against a human opponent, are a novel problem with multifaceted challenges. Accurate dynamic trajectory generation in order to respond to the tennis ball from the opponent and a novel control scheme for robust and high-performance tracking of the ball in such dynamic situations is a prerequisite to winning the game. In this paper, the dynamic movement primitives (DMPs) are employed for the stable generation of dynamic trajectories in the presence of environmental uncertainties such as ball position and velocity, opponent position and velocity and so on. …
Translating Counting Problems Into Computable Language Expressions, Zach Prescott
Translating Counting Problems Into Computable Language Expressions, Zach Prescott
Theses
The realm of automated problem solving is a relatively new field, even in the context of natural language processing. One area where this is often demonstrated is that of creating a program that can solve word problems. The program must understand the problem, perform some processing, and then convey this information to a user in a way that is accessible and understandable. There has been quite a lot of progress in this area with simpler problems. However, when it comes to understanding problems that involve a level of NLP, the results are not conclusive. In this paper, we would like …
Sentiment Analysis In Peer Review, Zachariah J. Beasley
Sentiment Analysis In Peer Review, Zachariah J. Beasley
USF Tampa Graduate Theses and Dissertations
Sentiment analysis, a widely popular subfield of natural language processing, has recently been used in the classroom to predict student attrition or to determine the mood of students, teacher strengths and weaknesses, or student perception of internship experience. These are all helpful indicators for the enhancement of students' academic experience but none improve the information gathered from or the reliability of peer review. This is particularly important in large courses with complex assignments (e.g., essays, software projects, and presentations) where scalable grading is requisite. In this dissertation, we apply sentiment analysis not on an assignment itself, but on the meaningful …
Modeling Multi-Targets Sentiment Classification Via Graph Convolutional Networks And Auxiliary Relation, Ao Feng, Zhengjie Gao, Xinyu Song, Ke Ke, Tianhao Xu, Xuelei Zhang
Modeling Multi-Targets Sentiment Classification Via Graph Convolutional Networks And Auxiliary Relation, Ao Feng, Zhengjie Gao, Xinyu Song, Ke Ke, Tianhao Xu, Xuelei Zhang
All Faculty Scholarship for the College of the Sciences
Existing solutions do not work well when multi-targets coexist in a sentence. The reason is that the existing solution is usually to separate multiple targets and process them separately. If the original sentence has N target, the original sentence will be repeated for N times, and only one target will be processed each time. To some extent, this approach degenerates the fine-grained sentiment classification task into the sentencelevel sentiment classification task, and the research method of processing the target separately ignores the internal relation and interaction between the targets. Based on the above considerations, we proposes to use Graph Convolutional …
Pathways To The Native Storyteller: A Method To Enable Computational Story Understanding, Aramide O. Kehinde
Pathways To The Native Storyteller: A Method To Enable Computational Story Understanding, Aramide O. Kehinde
College of Computing and Digital Media Dissertations
The primary objective of this thesis is to develop a method that uses machine learning algorithms to enable computational story understanding. This research is conducted with the aim of establishing a system called the Native Storyteller that plans and creates storytelling experiences for human users. The paper first establishes the desired capabilities of the system and then deep dives into how to enable story understanding, which is the core ability the system needs to function. As such, the research places emphasis on natural language processing and its application to solving key problems in this context. Namely, machine representation of story …
Name-Embedded Couplet Creation Based On Mobile Platform, Weihua Shen, Shicheng Zhang, Shunting Wang, Zhigeng Pan
Name-Embedded Couplet Creation Based On Mobile Platform, Weihua Shen, Shicheng Zhang, Shunting Wang, Zhigeng Pan
Journal of System Simulation
Abstract: Couplet culture is the crystallization of Chinese traditional culture, and also is the gem of Chinese language. Given the broad mobile intelligent terminal user groups, in order to inherit and carry forward the Chinese traditional culture, Android and iOS system were taken as the design platform, combining the couplet culture and modern science and technology in an organic whole based on the study of name-embedded couplet generation algorithm. The users were allowed to get personalized couplet belong to themselves conveniently and quickly by mobile platform. The name-embedded couplet creation software was expounded in the following areas: design concept, …
Skylight Opening Degree Prediction Method Based On Parallel Clustering, Deng Li, Yu Yue, Honglin Pang, Minrui Fei
Skylight Opening Degree Prediction Method Based On Parallel Clustering, Deng Li, Yu Yue, Honglin Pang, Minrui Fei
Journal of System Simulation
Abstract: To process the massive distributed data and control the agricultural facilities intelligently, a parallel Dirichlet Process Mixture Model (DPMM) clustering method was proposed based on Spark. With this method, the prediction model of greenhouse skylight opening degree was obtained by training the agricultural environmental and facilities data. The model was used to predict the greenhouse skylight opening degree. Through several comparison experiments, both the feasibility and the efficiency of the proposed parallel clustering were verified, the prediction accuracy was calculated. The experimental results show that the proposed approach has higher efficiency and accuracy.
Radar Emitter Signal Identification Based On Slide+Svm, Yingkun Huang, Weidong Jin
Radar Emitter Signal Identification Based On Slide+Svm, Yingkun Huang, Weidong Jin
Journal of System Simulation
Abstract: For the deficiency of traditional techniques of emitter signal feature extraction which heavily rely on experience, a model of radar emitting signal identification based on feature self-learning was proposed. This model consists of following 2 parts. Firstly, transform radar signal into frequency domain, then reduce signal dimension by using improved Piecewise Aggregate Approximation (PAA) method. Secondly, create the model of multi-layer Liner Denoiser (LIDE) to feature learning by using unsupervised training method. The validity of model was verified by simulating 5 different kinds of emitting signal with the outcome that excellent identification accuracy could be achieved at …
Research Of Chinese Diphthongs Pronunciation Based On Diva Model, Shaobai Zhang, Yanli Chen, Liwen He
Research Of Chinese Diphthongs Pronunciation Based On Diva Model, Shaobai Zhang, Yanli Chen, Liwen He
Journal of System Simulation
Abstract: DIVA (Directions Into Velocities of Articulators) is a kind of adaptive neural network model which is used to simulate and describe some associative functions in brain regions involved speech production and understanding. DIVA takes 29 essential English phonemes as its language background. Since the number of Chinese pronunciation phonemes is much larger than English and the pronunciation brain mechanisms of both also make a big difference, the adaptability of DIVA model for Chinese background has to be studied specially, in order that the model can read out the thinking processes in Chinese brain. Based on DIVA, the Chinese pronunciation …
Label Noise Reduction Without Assumptions, Jason Wei
Label Noise Reduction Without Assumptions, Jason Wei
Dartmouth College Undergraduate Theses
We propose an algorithm for training neural networks in noisy label scenarios that up-weighs per-example gradients that are more similar to other gradients in the same minibatch. Our approach makes no assumptions about the amount or type of label noise, does not use a held-out validation set of clean examples, makes relatively few computations, and only modifies the minibatch gradient aggregation module in a typical neural network training workflow. For CIFAR-10 classification with varying levels of label noise, our method successfully up-weighs clean examples and de-prioritizes noisy examples, showing consistent improvement over a vanilla training baseline. Our results open the …
Natural Invariance Explains Empirical Success Of Specific Membership Functions, Hedge Operations, And Negation Operations, Julio Urenda, Orsoly Csiszár, Gábor Csiszár, József Dombi, György Eigner, Vladik Kreinovich
Natural Invariance Explains Empirical Success Of Specific Membership Functions, Hedge Operations, And Negation Operations, Julio Urenda, Orsoly Csiszár, Gábor Csiszár, József Dombi, György Eigner, Vladik Kreinovich
Departmental Technical Reports (CS)
Empirical studies have shown that in many practical problems, out of all symmetric membership functions, special distending functions work best, and out of all hedge operations and negation operations, fractional linear ones work the best. In this paper, we show that these empirical successes can be explained by natural invariance requirements.
Survey On Individual Differences In Visualization, Zhengliang Liu, R. Jordan Crouser, Alvitta Ottley
Survey On Individual Differences In Visualization, Zhengliang Liu, R. Jordan Crouser, Alvitta Ottley
Computer Science: Faculty Publications
Developments in data visualization research have enabled visualization systems to achieve great general usability and application across a variety of domains. These advancements have improved not only people's understanding of data, but also the general understanding of people themselves, and how they interact with visualization systems. In particular, researchers have gradually come to recognize the deficiency of having one-size-fits-all visualization interfaces, as well as the significance of individual differences in the use of data visualization systems. Unfortunately, the absence of comprehensive surveys of the existing literature impedes the development of this research. In this paper, we review the research perspectives, …
Hyperbolic Visual Embedding Learning For Zero-Shot Recognition, Shaoteng Liu, Jingjing Chen, Liangming Pan, Chong-Wah Ngo, Tat-Seng Chua, Yu-Gang Jiang
Hyperbolic Visual Embedding Learning For Zero-Shot Recognition, Shaoteng Liu, Jingjing Chen, Liangming Pan, Chong-Wah Ngo, Tat-Seng Chua, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
This paper proposes a Hyperbolic Visual Embedding Learning Network for zero-shot recognition. The network learns image embeddings in hyperbolic space, which is capable of preserving the hierarchical structure of semantic classes in low dimensions. Comparing with existing zeroshot learning approaches, the network is more robust because the embedding feature in hyperbolic space better represents class hierarchy and thereby avoid misleading resulted from unrelated siblings. Our network outperforms exiting baselines under hierarchical evaluation with an extremely challenging setting, i.e., learning only from 1,000 categories to recognize 20,841 unseen categories. While under flat evaluation, it has competitive performance as state-of-the-art methods but …
Empirical Evaluation Of Three Common Assumptions In Building Political Media Bias Datasets, Soumen Ganguly, Juhi Kulshrestha, Jisun An, Haewoon Kwak
Empirical Evaluation Of Three Common Assumptions In Building Political Media Bias Datasets, Soumen Ganguly, Juhi Kulshrestha, Jisun An, Haewoon Kwak
Research Collection School Of Computing and Information Systems
In this work, we empirically validate three common assumptions in building political media bias datasets, which are (i) labelers' political leanings do not affect labeling tasks, (ii) news articles follow their source outlet's political leaning, and (iii) political leaning of a news outlet is stable across different topics. We build a ground-truth dataset of manually annotated article-level political leaning and validate the three assumptions. Our findings warn that the three assumptions could be invalid even for a small dataset. We hope that our work calls attention to the (in)validity of common assumptions in building political media bias datasets.
Knowledge Enhanced Neural Fashion Trend Forecasting, Yunshan Ma, Yujuan Ding, Xun Yang, Lizi Liao, Wai Keung Wong, Tat-Seng Chua
Knowledge Enhanced Neural Fashion Trend Forecasting, Yunshan Ma, Yujuan Ding, Xun Yang, Lizi Liao, Wai Keung Wong, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Fashion trend forecasting is a crucial task for both academia andindustry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal thereal fashion trends. Towards insightful fashion trend forecasting,this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from Instagram with extracted time series fashion element records and user information. Furthermore, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Knowledge Enhanced …
Self-Trained Deep Ordinal Regression For End-To-End Video Anomaly Detection, Guansong Pang, Cheng Yan, Chunhua Shen, Anton Van Den Hengel, Xiao Bai
Self-Trained Deep Ordinal Regression For End-To-End Video Anomaly Detection, Guansong Pang, Cheng Yan, Chunhua Shen, Anton Van Den Hengel, Xiao Bai
Research Collection School Of Computing and Information Systems
Depression is among the most prevalent mental disorders, affecting millions of people of all ages globally. Machine learning techniques have shown effective in enabling automated detection and prediction of depression for early intervention and treatment. However, they are challenged by the relative scarcity of instances of depression in the data. In this work we introduce a novel deep multi-task recurrent neural network to tackle this challenge, in which depression classification is jointly optimized with two auxiliary tasks, namely one-class metric learning and anomaly ranking. The auxiliary tasks introduce an inductive bias that improves the classification model’s generalizability on small depression …