Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- Singapore Management University (1121)
- TÜBİTAK (210)
- Wright State University (197)
- Technological University Dublin (192)
- University of New Mexico (165)
-
- Old Dominion University (143)
- Claremont Colleges (126)
- Missouri University of Science and Technology (125)
- University of Nebraska - Lincoln (125)
- San Jose State University (119)
- City University of New York (CUNY) (117)
- Brigham Young University (105)
- Neutrosophic Systems with Applications (92)
- University of Texas at El Paso (88)
- University of Northern Iowa (78)
- University of South Florida (78)
- Chulalongkorn University (73)
- Dartmouth College (72)
- MBZUAI (70)
- Kennesaw State University (66)
- Portland State University (62)
- Zayed University (62)
- Chapman University (60)
- New Jersey Institute of Technology (57)
- Boise State University (56)
- Edith Cowan University (56)
- University of Arkansas, Fayetteville (55)
- University of Nevada, Las Vegas (53)
- Purdue University (51)
- University of Texas Rio Grande Valley (51)
- Keyword
-
- Machine learning (212)
- Natural language processing (211)
- Artificial intelligence (157)
- Natural Language Processing (155)
- Machine Learning (147)
-
- Deep learning (132)
- Artificial Intelligence (101)
- Large language models (88)
- Computer Science (84)
- Social media (83)
- NLP (76)
- Twitter (70)
- Sentiment analysis (69)
- Mathematics (68)
- Deep Learning (67)
- Large Language Models (62)
- Text mining (59)
- Neural networks (58)
- Computational linguistics (54)
- Computer science (53)
- Department of Computer Science and Engineering (53)
- Education (49)
- Fuzzy logic (49)
- Generative AI (49)
- AI (48)
- Data mining (47)
- Linguistics (43)
- Classification (41)
- Social Media (39)
- Information retrieval (38)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (1037)
- Theses and Dissertations (224)
- Turkish Journal of Electrical Engineering and Computer Sciences (199)
- Branch Mathematics and Statistics Faculty and Staff Publications (150)
- Master's Projects (99)
-
- Conference papers (96)
- Neutrosophic Systems with Applications (92)
- Kno.e.sis Publications (84)
- Dissertations (83)
- Chulalongkorn University Theses and Dissertations (Chula ETD) (70)
- Computer Science Faculty Research & Creative Works (66)
- Electronic Theses and Dissertations (65)
- Journal of Humanistic Mathematics (63)
- All Works (62)
- Browse all Theses and Dissertations (62)
- Computer Science Faculty Publications (59)
- Faculty Publications (59)
- USF Tampa Graduate Theses and Dissertations (55)
- Publications and Research (51)
- Iowa Academy of Science Documents (50)
- Computer Science Faculty Publications and Presentations (45)
- Departmental Technical Reports (CS) (44)
- Dissertations, Theses, and Capstone Projects (44)
- Articles (42)
- Faculty, Staff and Student Publications (42)
- Open Access Theses & Dissertations (42)
- Journal of Informatics and Web Engineering (41)
- SMU Data Science Review (41)
- Walden Dissertations and Doctoral Studies (39)
- Computer Science and Engineering Faculty Publications (38)
- Publication Type
- File Type
Articles 3661 - 3690 of 6327
Full-Text Articles in Entire DC Network
Psychological Behavior Of English Learners Utilizing A Cognitive Tutor In An Online Pre-Calculus, Julian Viera Jr., Olga Kosheleva, Vladik Kreinovich
Psychological Behavior Of English Learners Utilizing A Cognitive Tutor In An Online Pre-Calculus, Julian Viera Jr., Olga Kosheleva, Vladik Kreinovich
Departmental Technical Reports (CS)
The educational landscape is becoming a digital learning environment. Students in today's digital world draw from multiple sources of information; from hypertext, videos, social media, to video games and internet searches. English Learners, individuals learning two languages at once, who use software written in English have a passive relationship with the computer when software is not in their native language. They feel that this educational software belongs to another culture. This paper will present findings from a study with English Learners' engagement in a fully online pre-calculus course. The authors utilized Cultural-Historical Activity Theory to describe how English Learners' created …
Lecture: Intro To Data Science - Ml 3 - Week Eleven, Grant Long, Nyc Tech-In-Residence Corps
Lecture: Intro To Data Science - Ml 3 - Week Eleven, Grant Long, Nyc Tech-In-Residence Corps
Open Educational Resources
Lecture for the course "CSC 59970: Intro to Data Science" (Week Eleven) delivered at the City College of New York in Fall 2018 by Grant Long as part of the Tech-in-Residence Corps program.
Predicting Visual Context For Unsupervised Event Segmentation In Continuous Photo-Streams, Ana García Del Molino, Joo-Hwee Lim, Ah-Hwee Tan
Predicting Visual Context For Unsupervised Event Segmentation In Continuous Photo-Streams, Ana García Del Molino, Joo-Hwee Lim, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
Segmenting video content into events provides semantic structures for indexing, retrieval, and summarization. Since motion cues are not available in continuous photo-streams, and annotations in lifelogging are scarce and costly, the frames are usually clustered into events by comparing the visual features between them in an unsupervised way. However, such methodologies are ineffective to deal with heterogeneous events, e.g. taking a walk, and temporary changes in the sight direction, e.g. at a meeting. To address these limitations, we propose Contextual Event Segmentation (CES), a novel segmentation paradigm that uses an LSTM-based generative network to model the photo-stream sequences, predict their …
Automating Intention Mining, Qiao Huang, Xin Xia, David Lo, Gail C. Murphy
Automating Intention Mining, Qiao Huang, Xin Xia, David Lo, Gail C. Murphy
Research Collection School Of Computing and Information Systems
Developers frequently discuss aspects of the systems they are developing online. The comments they post to discussions form a rich information source about the system. Intention mining, a process introduced by Di Sorbo et al., classifies sentences in developer discussions to enable further analysis. As one example of use, intention mining has been used to help build various recommenders for software developers. The technique introduced by Di Sorbo et al. to categorize sentences is based on linguistic patterns derived from two projects. The limited number of data sources used in this earlier work introduces questions about the comprehensiveness of intention …
Fully Convolutional Neural Networks For Pixel Classification In Historical Document Images, Seth Andrew Stewart
Fully Convolutional Neural Networks For Pixel Classification In Historical Document Images, Seth Andrew Stewart
Theses and Dissertations
We use a Fully Convolutional Neural Network (FCNN) to classify pixels in historical document images, enabling the extraction of high-quality, pixel-precise and semantically consistent layers of masked content. We also analyze a dataset of hand-labeled historical form images of unprecedented detail and complexity. The semantic categories we consider in this new dataset include handwriting, machine-printed text, dotted and solid lines, and stamps. Segmentation of document images into distinct layers allows handwriting, machine print, and other content to be processed and recognized discriminatively, and therefore more intelligently than might be possible with content-unaware methods. We show that an efficient FCNN with …
Deep Understanding Of Cooking Procedure For Cross-Modal Recipe Retrieval, Jingjing Chen, Chong-Wah Ngo, Fu-Li Feng, Tat-Seng Chua
Deep Understanding Of Cooking Procedure For Cross-Modal Recipe Retrieval, Jingjing Chen, Chong-Wah Ngo, Fu-Li Feng, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Finding a right recipe that describes the cooking procedure for a dish from just one picture is inherently a difficult problem. Food preparation undergoes a complex process involving raw ingredients, utensils, cutting and cooking operations. This process gives clues to the multimedia presentation of a dish (e.g., taste, colour, shape). However, the description of the process is implicit, implying only the cause of dish presentation rather than the visual effect that can be vividly observed on a picture. Therefore, different from other cross-modal retrieval problems in the literature, recipe search requires the understanding of textually described procedure to predict its …
Interfacing Iconicity - Addressing Software Divarication Through Diagrammatic Design Principles, George Akhvlediani
Interfacing Iconicity - Addressing Software Divarication Through Diagrammatic Design Principles, George Akhvlediani
Theses and Dissertations
This research examines conflicts accompanying the proliferation of computer technology and, more specifically, constellations of dependency in the always expanding volume of software, platforms, and the firms/individuals using them. We identify a pervasive phenomenon of “divarication” in the growing variety of progressively specialized systems and system roles. As software systems enter new thresholds of sophistication, they effectively aggregate many distinct components and protocols. Consequently, we are confronted with a diverse ecology of stratified and thereby incompatible software systems. Software inherits the limitations and potential flaws of its constituent parts, but unlike physical machinery, it isn’t readily disassembled in instances of …
An Evaluation Of Geotagged Twitter Data During Hurricane Irma Using Sentiment Analysis And Topic Modeling For Disaster Resilience, Ike Robert Vayansky
An Evaluation Of Geotagged Twitter Data During Hurricane Irma Using Sentiment Analysis And Topic Modeling For Disaster Resilience, Ike Robert Vayansky
Electronic Theses and Dissertations
Disasters require quick response times, thought-out preparations, overall community, and government support. These efforts will ensure prevention of loss of life and reduce possible damages. The United States has been battered by multiple major hurricanes in the recent years and multiple avenues of disaster response efforts were being tested. Hurricane Irma can be recognized as the most popular hurricane in terms of social media attention. Irma made landfall in Florida as a Category 4 storm and preparation measures taken were intensive thus providing a good measure to evaluate in terms of efficacy. The effectiveness of the response methods utilized are …
Categorizing The Content Of Github Readme Files, Gede Artha Azriadi Prana, Christoph Treude, Ferdian Thung, Thushari Atapattu, David Lo
Categorizing The Content Of Github Readme Files, Gede Artha Azriadi Prana, Christoph Treude, Ferdian Thung, Thushari Atapattu, David Lo
Research Collection School Of Computing and Information Systems
README files play an essential role in shaping a developer’s first impression of a software repository and in documenting the software project that the repository hosts. Yet, we lack a systematic understanding of the content of a typical README file as well as tools that can process these files automatically. To close this gap, we conduct a qualitative study involving the manual annotation of 4,226 README file sections from 393 randomly sampled GitHub repositories and we design and evaluate a classifier and a set of features that can categorize these sections automatically. We find that information discussing the ‘What’ and …
Multiperspective Graph-Theoretic Similarity Measure, Dung D. Le, Hady W. Lauw
Multiperspective Graph-Theoretic Similarity Measure, Dung D. Le, Hady W. Lauw
Research Collection School Of Computing and Information Systems
Determining the similarity between two objects is pertinent to many applications. When the basis for similarity is a set of object-to-object relationships, it is natural to rely on graph-theoretic measures. One seminal technique for measuring the structural-context similarity between a pair of graph vertices is SimRank, whose underlying intuition is that two objects are similar if they are connected by similar objects. However, by design, SimRank as well as its variants capture only a single view or perspective of similarity. Meanwhile, in many real-world scenarios, there emerge multiple perspectives of similarity, i.e., two objects may be similar from one perspective, …
From Tag To Protect: A Tag-Driven Policy Recommender System For Image Sharing, Anna Cinzia Squicciarini, Andrea Novelli, Dan Lin, Cornelia Caragea, Haoti Zhong
From Tag To Protect: A Tag-Driven Policy Recommender System For Image Sharing, Anna Cinzia Squicciarini, Andrea Novelli, Dan Lin, Cornelia Caragea, Haoti Zhong
Computer Science Faculty Research & Creative Works
Sharing images on social network sites has become a part of daily routine for more and more online users. However, in face of the considerable number of images shared online, it is not a trivial task for a person to manually configure proper privacy settings for each of the images that he/she uploaded. The lack of proper privacy protection during image sharing could raise many potential privacy breaches of people's private lives that they are not aware of. In this work, we propose a privacy setting recommender system to help people effortlessly set up the privacy settings for their online …
Evaluating Prose Style Transfer With The Bible, Keith Carlson, Allen Riddell, Daniel Rockmore
Evaluating Prose Style Transfer With The Bible, Keith Carlson, Allen Riddell, Daniel Rockmore
Dartmouth Scholarship
In the prose style transfer task a system, provided with text input and a target prose style, produces output which preserves the meaning of the input text but alters the style. These systems require parallel data for evaluation of results and usually make use of parallel data for training. Currently, there are few publicly available corpora for this task. In this work, we identify a high-quality source of aligned, stylistically distinct text in different versions of the Bible. We provide a standardized split, into training, development and testing data, of the public domain versions in our corpus. This corpus is …
Using Chronicling America’S Images To Explore Digitized Historic Newspapers & Imagine Alternative Futures, Elizabeth Lorang, Leen-Kiat Soh
Using Chronicling America’S Images To Explore Digitized Historic Newspapers & Imagine Alternative Futures, Elizabeth Lorang, Leen-Kiat Soh
University of Nebraska-Lincoln Libraries: Presentations
This presentation situates the work of the Aida team broadly as well as hinges this work on some very specific challenges for digital libraries. In doing so demonstrate the many types of questions and domains to be explored in digitized newspapers.
Tourism Review Sentiment Classification Using A Bidirectional Recurrent Neural Network With An Attention Mechanism And Topic-Enriched Word Vectors, Qin Li, Shaobo Li, Jie Hu, Sen Zhang, Jianjun Hu
Tourism Review Sentiment Classification Using A Bidirectional Recurrent Neural Network With An Attention Mechanism And Topic-Enriched Word Vectors, Qin Li, Shaobo Li, Jie Hu, Sen Zhang, Jianjun Hu
Faculty Publications
Sentiment analysis of online tourist reviews is playing an increasingly important role in tourism. Accurately capturing the attitudes of tourists regarding different aspects of the scenic sites or the overall polarity of their online reviews is key to tourism analysis and application. However, the performances of current document sentiment analysis methods are not satisfactory as they either neglect the topics of the document or do not consider that not all words contribute equally to the meaning of the text. In this work, we propose a bidirectional gated recurrent unit neural network model (BiGRULA) for sentiment analysis by combining a topic …
Building Classifiers With Gmdh For Health Social Networks (Bd Askapatient), John Cardiff, Liliya Akhtyamova, Mikhail Alexandrov
Building Classifiers With Gmdh For Health Social Networks (Bd Askapatient), John Cardiff, Liliya Akhtyamova, Mikhail Alexandrov
Conference Papers
Health social media offer useful data for patients and doctors concerning both various medicines and treatments. Usually, these data are accompanied by their assessments in 5- star scale. But such a detail classification has small usefulness because patients and doctors, first of all, want to know about negative cases and to study in detail the extreme ones. In the paper we build classifiers of texts just for these cases using combined classes as negative, all others and worst, satisfactory, best. For this, we study possibilities of different GMDH-based algorithms and compare them with the results of other methods. The selection …
Entity-Grounded Image Captioning, Annika Lindh, Robert J. Ross, John D. Kelleher
Entity-Grounded Image Captioning, Annika Lindh, Robert J. Ross, John D. Kelleher
Conference papers
An urgent limitation in current Image Captioning models is their tendency to produce generic captions that avoid the interesting detail which makes each image unique. To address this limitation, we propose an approach that enforces a stronger alignment between image regions and specific segments of text. The model architecture is composed of a visual region proposer, a region-order planner and a region-guided caption generator. The region-guided caption generator incorporates a novel information gate which allows visual and textual input of different frequencies and dimensionalities in a Recurrent Neural Network.
Monitoring Scene Understanders With Conceptual Primitive Decomposition And Commonsense Knowledge, Leilani H. Gilpin, Jamie C. Macbeth, Evelyn Florentine
Monitoring Scene Understanders With Conceptual Primitive Decomposition And Commonsense Knowledge, Leilani H. Gilpin, Jamie C. Macbeth, Evelyn Florentine
Computer Science: Faculty Publications
Although there have been many key advancements in connecting text and perception, computer- generated image captions still lack common sense. As a first step towards constraining these perception mechanisms to commonsense judgment, we have developed reasonableness monitors: a wrapper interface that can explain if the descriptive output of an opaque deep neural network is plausible. These monitor a standalone system that uses careful dependency tracking, commonsense knowledge, and conceptual primitives to explain a perceived scene description to be reasonable or not. If such an explanation cannot be made, it is evidence that something unreasonable has been perceived. The development of …
Domain-Specific Knowledge Exploration With Ontology Hierarchical Re-Ranking And Adaptive Learning And Extension, Grace G. Zhao
Domain-Specific Knowledge Exploration With Ontology Hierarchical Re-Ranking And Adaptive Learning And Extension, Grace G. Zhao
Dissertations, Theses, and Capstone Projects
The goal of this research project is the realization of an artificial intelligence-driven lightweight domain knowledge search framework that returns a domain knowledge structure upon request with highly relevant web resources via a set of domain-centric re-ranking algorithms and adaptive ontology learning models. The re-ranking algorithm, a necessary mechanism to counter-play the heterogeneity and unstructured nature of web data, uses augmented queries and a hierarchical taxonomic structure to get further insight into the initial search results obtained from credited generic search engines. A semantic weight scale is applied to each node in the ontology graph and in turn generates a …
Personality Recognition For Deception Detection, Guozhen An
Personality Recognition For Deception Detection, Guozhen An
Dissertations, Theses, and Capstone Projects
Personality aims at capturing stable individual characteristics, typically measurable in quantitative terms, that explain and predict observable behavioral differences. Personality has been proved to be very useful in many life outcomes, and there has been huge interests on predicting personality automatically. Previously, there are tremendous amount of approaches successfully predicting personality. However, most previous research on personality detection has used personality scores assigned by annotators based solely on the text or audio clip, and found that predicting self-reported personality is a much more difficult task than predicting observer-report personality. In our study, we will demonstrate how to accurately detect self-reported …
Fake News Detection: A Deep Learning Approach, Aswini Thota, Priyanka Tilak, Simrat Ahluwalia, Nibrat Lohia
Fake News Detection: A Deep Learning Approach, Aswini Thota, Priyanka Tilak, Simrat Ahluwalia, Nibrat Lohia
SMU Data Science Review
Fake news is defined as a made-up story with an intention to deceive or to mislead. In this paper we present the solution to the task of fake news detection by using Deep Learning architectures. Gartner research [1] predicts that “By 2022, most people in mature economies will consume more false information than true information”. The exponential increase in production and distribution of inaccurate news presents an immediate need for automatically tagging and detecting such twisted news articles. However, automated detection of fake news is a hard task to accomplish as it requires the model to understand nuances in natural …
Yelp’S Review Filtering Algorithm, Yao Yao, Ivelin Angelov, Jack Rasmus-Vorrath, Mooyoung Lee, Daniel W. Engels
Yelp’S Review Filtering Algorithm, Yao Yao, Ivelin Angelov, Jack Rasmus-Vorrath, Mooyoung Lee, Daniel W. Engels
SMU Data Science Review
In this paper, we present an analysis of features influencing Yelp's proprietary review filtering algorithm. Classifying or misclassifying reviews as recommended or non-recommended affects average ratings, consumer decisions, and ultimately, business revenue. Our analysis involves systematically sampling and scraping Yelp restaurant reviews. Features are extracted from review metadata and engineered from metrics and scores generated using text classifiers and sentiment analysis. The coefficients of a multivariate logistic regression model were interpreted as quantifications of the relative importance of features in classifying reviews as recommended or non-recommended. The model classified review recommendations with an accuracy of 78%. We found that reviews …
A Linked Coptic Dictionary Online, Frank Feder, Maxim Kupreyev, Emma Manning, Caroline T. Schroeder, Amir Zeldes
A Linked Coptic Dictionary Online, Frank Feder, Maxim Kupreyev, Emma Manning, Caroline T. Schroeder, Amir Zeldes
College of the Pacific Faculty Presentations
We describe a new project publishing a freely available online dictionary for Coptic. The dictionary encompasses comprehensive cross-referencing mechanisms, including linking entries to an online scanned edition of Crum’s Coptic Dictionary, internal cross-references and etymological information, translated searchable definitions in English, French and German, and linked corpus data which provides frequencies and corpus look-up for headwords and multiword expressions. Headwords are available for linking in external projects using a REST API. We describe the challenges in encoding our dictionary using TEI XML and implementing linking mechanisms to construct a Web interface querying frequency information, which draw on NLP tools to …
Computational Thinking And Literacy, Sharin Rawhiya Jacob, Mark Warschauer
Computational Thinking And Literacy, Sharin Rawhiya Jacob, Mark Warschauer
Journal of Computer Science Integration
Today’s students will enter a workforce that is powerfully shaped by computing. To be successful in a changing economy, students must learn to think algorithmically and computationally, to solve problems with varying levels of abstraction. These computational thinking skills have become so integrated into social function as to represent fundamental literacies. However, computer science has not been widely taught in K-12 schools. Efforts to create computer science standards and frameworks have yet to make their way into mandated course requirements. Despite a plethora of research on digital literacies, research on the role of computational thinking in the literature is sparse. …
Syntactic Graduonymy, N. Abdullayeva
Syntactic Graduonymy, N. Abdullayeva
Scientific journal of the Fergana State University
This article is dedicated to the existence of graduonymy, which is considered as one of the modern linguistics’ new notions, in syntax. Moreover, graduonymic relations among syntactic units and phenomena, and their peculiarities are investigated; they are proved by some examples.
Syntactic Graduonymy, N. Abdullayeva
Syntactic Graduonymy, N. Abdullayeva
Scientific journal of the Fergana State University
This article is dedicated to the existence of graduonymy, which is considered as one of the modern linguistics’ new notions, in syntax. Moreover, graduonymic relations among syntactic units and phenomena, and their peculiarities are investigated; they are proved by some examples.
Enthymemathical Proofs And Canonical Proofs In Euclid’S Plane Geometry, Abel Lassalle, Marco Panza
Enthymemathical Proofs And Canonical Proofs In Euclid’S Plane Geometry, Abel Lassalle, Marco Panza
MPP Published Research
Since the application of Postulate I.2 in Euclid’s Elements is not uniform, one could wonder in what way should it be applied in Euclid’s plane geometry. Besides legitimizing questions like this from the perspective of a philosophy of mathematical practice, we sketch a general perspective of conceptual analysis of mathematical texts, which involves an extended notion of mathematical theory as system of authorizations, and an audience-dependent notion of proof.
Automatic Knowledge Extraction From Ocr Documents Using Hierarchical Document Analysis, Mohammad Masum, Sai Kosaraju, Tanju Bayramoglu, Girish Modgil, Mingon Kang
Automatic Knowledge Extraction From Ocr Documents Using Hierarchical Document Analysis, Mohammad Masum, Sai Kosaraju, Tanju Bayramoglu, Girish Modgil, Mingon Kang
Published and Grey Literature from PhD Candidates
Industries can improve their business efficiency by analyzing and extracting relevant knowledge from large numbers of documents. Knowledge extraction manually from large volume of documents is labor intensive, unscalable and challenging. Consequently, there have been a number of attempts to develop intelligent systems to automatically extract relevant knowledge from OCR documents. Moreover, the automatic system can improve the capability of search engine by providing application-specific domain knowledge. However, extracting the efficient information from OCR documents is challenging due to highly unstructured format. In this paper, we propose an efficient framework for a knowledge extraction system that takes keywords based queries …
Translating Global Nature: Territoriality, Environmental Discourses, And Ecocultural Identities, José R. Castro-Sotomayor
Translating Global Nature: Territoriality, Environmental Discourses, And Ecocultural Identities, José R. Castro-Sotomayor
Communication ETDs
In this study, I explore environmental discourses circulating among Indigenous transboundary organizations working on environmental initiatives at the border between Ecuador and Colombia. I focus on three global environmental discourses –sustainability, development, and climate change– as they are at the core of the global environmental governance vernacular. La Gran Familia Awá Binacional (GFAB), one of the few transboundary Indigenous organizations working along the binational border, utilizes these global concepts to frame their environmental initiatives and projects. I use a critical and interpretive qualitative approach to investigate, deconstruct, and rearticulate global environmental discourses circulating among and translated by two of the …
Spatio-Temporal Variations Of Soil Active Layer Thickness In Chinese Boreal Forests From 2000 To 2015, Xiongxiong Bai, Jian Yang, Bo Tao, Wei Ren
Spatio-Temporal Variations Of Soil Active Layer Thickness In Chinese Boreal Forests From 2000 To 2015, Xiongxiong Bai, Jian Yang, Bo Tao, Wei Ren
Forestry and Natural Resources Faculty Publications
The soil active layer in boreal forests is sensitive to climate warming. Climate-induced changes in the active layer may greatly affect the global carbon budget and planetary climatic system by releasing large quantities of greenhouse gases that currently are stored in permafrost. Ground surface temperature is an immediate driver of active layer thickness (ALT) dynamics. In this study, we mapped ALT distribution in Chinese boreal larch forests from 2000 to 2015 by integrating remote sensing data with the Stefan equation. We then examined the changes of the ALT in response to changes in ground surface temperature and identified drivers of …
Densely Connected Bidirectional Lstm With Applications To Sentence Classification, Zixiang Ding, Rui Xia, Jianfei Yu, Xiang Li, Jian Yang
Densely Connected Bidirectional Lstm With Applications To Sentence Classification, Zixiang Ding, Rui Xia, Jianfei Yu, Xiang Li, Jian Yang
Student Publications
Deep neural networks have recently been shown to achieve highly competitive performance in many computer vision tasks due to their abilities of exploring in a much larger hypothesis space. However, since most deep architectures like stacked RNNs tend to suffer from the vanishing-gradient and overfitting problems, their effects are still understudied in many NLP tasks. Inspired by this, we propose a novel multi-layer RNN model called densely connected bidirectional long short-term memory (DCBi-LSTM) in this paper, which essentially represents each layer by the concatenation of its hidden state and all preceding layers’ hidden states, followed by recursively passing each layer’s …