Home
Search results “Semantic web mining algorithms psychology”
Where NLP and psychology meet - Alexandra Klochko
 
33:03
PyData Berlin 2018 Company culture was identified as the most significant barrier to effectiveness. The first part of a talk offers lessons of how NLP can be used to break through first steps of solving issues such as quantifying organizational culture without surveys. I will demonstrate scoring engine that was created to help with it. Second part will cover insights that we found applying this engine. --- www.pydata.org PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases.
Views: 442 PyData
Social Network Analysis
 
02:06:01
An overview of social networks and social network analysis. See more on this video at https://www.microsoft.com/en-us/research/video/social-network-analysis/
Views: 4602 Microsoft Research
A Story of Discrimination and Unfairness (33c3)
 
34:56
https://media.ccc.de/v/33c3-8026-a_story_of_discrimination_and_unfairness Prejudice in Word Embeddings Artificial intelligence and machine learning are in a period of astounding growth. However, there are concerns that these technologies may be used, either with or without intention, to perpetuate the prejudice and unfairness that unfortunately characterizes many human institutions. We show for the first time that human-like semantic biases result from the application of standard machine learning to ordinary language—the same sort of language humans are exposed to every day. We replicate a spectrum of standard human biases as exposed by the Implicit Association Test and other well-known psychological studies. We replicate these using a widely used, purely statistical machine-learning model—namely, the GloVe word embedding—trained on a corpus of text from the Web. Our results indicate that language itself contains recoverable and accurate imprints of our historic biases, whether these are morally neutral as towards insects or flowers, problematic as towards race or gender, or even simply veridical, reflecting the status quo for the distribution of gender with respect to careers or first names. These regularities are captured by machine learning along with the rest of semantics. In addition to our empirical findings concerning language, we also contribute new methods for evaluating bias in text, the Word Embedding Association Test (WEAT) and the Word Embedding Factual Association Test (WEFAT). Our results have implications not only for AI and machine learning, but also for the fields of psychology, sociology, and human ethics, since they raise the possibility that mere exposure to everyday language can account for the biases we replicate here. ['Aylin Caliskan']
Views: 1536 media.ccc.de
Mod-01 Lec-23 CLIA; IR Basics
 
49:25
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Views: 1988 nptelhrd
Moral Math of Robots: Can Life and Death Decisions Be Coded?
 
01:32:08
A self-driving car has a split second to decide whether to turn into oncoming traffic or hit a child who has lost control of her bicycle. An autonomous drone needs to decide whether to risk the lives of busload of civilians or lose a long-sought terrorist. How does a machine make an ethical decision? Can it “learn” to choose in situations that would strain human decision making? Can morality be programmed? We will tackle these questions and more as the leading AI experts, roboticists, neuroscientists, and legal experts debate the ethics and morality of thinking machines. This program is part of the Big Ideas Series, made possible with support from the John Templeton Foundation. Subscribe to our YouTube Channel for all the latest from WSF. Visit our Website: http://www.worldsciencefestival.com/ Like us on Facebook: https://www.facebook.com/worldsciencefestival Follow us on twitter: https://twitter.com/WorldSciFest Original Program Date: June 4, 2016 MODERATOR: Bill Blakemore PARTICIPANTS: Fernando Diaz, Colonel Linell Letendre, Gary Marcus, Matthias Scheutz, Wendell Wallach Can Life and Death Decisions Be Coded? 00:06 Siri... What is the meaning of life? 1:49 Participant introductions 4:01 Asimov's Three Laws of Robotics 6:22 In 1966 ELIZA was one of the first artificial intelligence systems. 10:20 What is ALPHAGO? 15:43 TAY Tweets the first AI twitter bot. 19:25 Can you test learning Systems? 26:31 Robots and automatic reasoning demonstration 30:31 How do driverless cars work? 39:32 What is the trolley problem? 49:00 What is autonomy in military terms? 56:40 Are landmines the first automated weapon? 1:10:30 Defining how artificial intelligence learns 1:16:03 Using Minecraft to teach AI about humans and their interactions 1:22:27 Should we be afraid that AI will take over the world? 1:25:08
Views: 47402 World Science Festival
Rhythms of Information Flow through Networks
 
01:22:22
8th Extended Semantic Web Conference (ESWC) 2011 View the complete lectures: http://videolectures.net/eswc2011_heraklion/ Speaker: Jure Leskovec, Computer Science Department, Stanford University License: Creative Commons CC BY-NC-ND 3.0 More information at http://videolectures.net/site/about/ More talks at http://videolectures.net/ The information we experience online comes to us continuously over time, assembled from many small pieces, and conveyed through our social networks. This merging of information, network structure, and flow over time requires new ways of reasoning about the large-scale behavior of information networks. I will discuss a set of approaches for tracking information as it travels and mutates in online networks. We show how to capture and model temporal patterns in the news over a daily time-scale -- in particular, the succession of story lines that evolve and compete for attention. I will also discuss models to quantify the influence of individual media sites on the popularity of news stories and algorithms for inferring latent information diffusion networks. 0:00 Rhythms of Information Flow through Networks 3:58 Information and Network 5:16 Online (Social) Media 6:34 Social Media: The New Picture 7:55 Information: Heavily dynamic 8:42 Plan for the talk 9:44 Challenges and Opportunities 11:29 Extracting Units of Information 14:02 Information Cascades in Blogs 15:45 Meme - tracking 18:10 Finding Mutational Variants 20:48 Cluster Volume over Time - 1 21:09 Cluster Volume over Time - 2 23:26 Interaction of News and Blogs 25:57 Patterns of Information Attention
Views: 1279 VideoLecturesChannel
Social web sentiment strength detection: methods and issues. Mike Thelwall. Cyberemotions 2013.
 
47:35
Mike Thelwall, Cyberemotions Project Member Collective Emotions in Cyberspace Final Conference of EU Project CYBEREMOTIONS 2013 http://www.cyberemotions.eu/ 29-30 January 2013, Faculty of Physics, Warsaw University of Technology Lectures at Final Conference of EU Project CYBEREMOTIONS, Warsaw University of Technology, 29-30 Jan. 2013. 1. Collective emotions in Cyberspace, short review of Cyberemotions Project results, Janusz Hołyst http://www.youtube.com/watch?v=5VOaxNQoZK0 2. The Psychology of (Cyber)Emotions, Arvid Kappas http://www.youtube.com/watch?v=Rewpvvyqqxk 3. The social sharing of emotion, Bernard Rimé http://www.youtube.com/watch?v=x2G-afWwrco 4. How Emotional Are Users Needs? Emotion in Query Logs, Marina Santini http://www.youtube.com/watch?v=CJkyFKL5Y3A 5. Social web sentiment strength detection: methods and issues, Mike Thelwall http://www.youtube.com/watch?v=7ZhijBzLf-4 6. Dynamics of emotions in voice during real-life arguments, Magdalena Igras http://www.youtube.com/watch?v=XWTKRLFeLnQ 7. Application of semantic spaces to sentiment analysis for words, Marcin Tatjewski http://www.youtube.com/watch?v=cv1ICNAhnuw 8. Online Networks and the Diffusion of Protests, Yamir Moreno http://www.youtube.com/watch?v=_iCy0v4nz8Y 9. The impact of cyberspace upon current society, Aaron Ben-Ze'ev http://www.youtube.com/watch?v=o3Uz9EsQjBc 10. Online discussions modelled by an evolving Ising-like dynamics, Julian Sienkiewicz http://www.youtube.com/watch?v=2gCkhOeAMBs 11. A modelling framework for collective emotions in online communities, David Garcia http://www.youtube.com/watch?v=_FoEGCAes_0 12. Patterns of Online Chats with Emotional Bots: Data Analysis and Agent-Based Simulations, Vladimir Gligorijević http://www.youtube.com/watch?v=Ex815-jljkw 13. Transition due to preferential cluster growth of collective emotions in online communities, Anna Chmiel http://www.youtube.com/watch?v=oAVIn1YUBvM 14. Psychological Aspects of Social Communities, Renaud Lambiotte http://www.youtube.com/watch?v=2Z3y58KAgys 15. The Simmel effect and babies names, Krzysztof Kułakowski http://www.youtube.com/watch?v=q3bDg-T90E4 16. A new model of individual opinion dynamics based on information and emotions, Paweł Sobkowicz http://www.youtube.com/watch?v=JUyRfKQITis 17. Human behavior in online social networks, Andrzej Grabowski http://www.youtube.com/watch?v=WfFHJNUz0gU 18. Facial asymmetry and affective communication in 3D Online Virtual Society, Junghyun Ahn http://www.youtube.com/watch?v=WZOI3ou3bFU
Views: 592 fensPW
Interoperability of Text Corpus Annotations with the Semantic Web
 
21:05
Original version is http://togotv.dbcls.jp/20150321.html Biomedical Linked Annotation Hackathon (BLAH) 2015 was held in The University of Tokyo Kashiwa Campus Station Satellite in Kashiwa, Chiba, Japan. On the last day of the Hackathon (Feb. 27), public symposium of the BLAH 2015 was held. In this talk, Karin Verspoor (University of Melbourne) makes a presentation entitled "Interoperability of Text Corpus Annotations with the Semantic Web". (21:05)
Views: 138 togotv
Kriton Speech: Knowledge Acquisition for Ontologies - Depression
 
03:32
Kriton Speech is a general purpose knowledge acquisition tool incorporating a variety of elicitation methods, such as interview techniques, protocol analysis, text mining and machine learning. Psychological interview techniques are used to obtain domain knowledge from an expert, in this case a clinical psychologist. Kriton Speech uses voice as the user interface. The system interviews the user and as a result, builds ontologies and rule-based systems. The output is a Web Ontology Language (OWL) file that can be edited by use of ontology editors such as Protege. Please see http://psychologynetwork.com.au/KritonSpeechWhitePaper.pdf. For more information, email [email protected]
Views: 94 Psychology Network
Protecting Your Right: Verifiable Attribute-based Keyword Search with Fine-grained
 
16:03
Protecting Your Right: Verifiable Attribute-based Keyword Search with Fine-grained - IEEE PROJECTS 2016-2017 HOME PAGE : http://www.micansinfotech.com/index.html CSE VIDEOS : http://www.micansinfotech.com/VIDEOS-2017-2018.html ANDROID VIDEOS : http://www.micansinfotech.com/VIDEOS-ANDROID-2017-2018.html PHP VIDEOS : http://www.micansinfotech.com/VIDEOS-APPLICATION-PROJECT-2017-2018#PHP APPLICATION VIDEOS : http://www.micansinfotech.com/VIDEOS-APPLICATION-PROJECT-2017-2018.html CSE IEEE TITLES : http://www.micansinfotech.com/IEEE-PROJECTS-CSE-2017-2018.html EEE TITLES : http://www.micansinfotech.com/IEEE-PROJECTS-POWERELECTRONICS-2017-2018.html MECHANICAL TITLES : http://www.micansinfotech.com/IEEE-PROJECTS-MECHANICAL-FABRICATION-2017-2018.html CONTACT US : http://www.micansinfotech.com/CONTACT-US.html MICANS INFOTECH offers Projects in CSE ,IT, EEE, ECE, MECH , MCA. MPHIL , BSC, in various domains JAVA ,PHP, DOT NET , ANDROID , MATLAB , NS2 , EMBEDDED , VLSI , APPLICATION PROJECTS , IEEE PROJECTS. CALL : +91 90036 28940 +91 94435 11725 [email protected] WWW.MICANSINFOTECH.COM Output Videos… IEEE PROJECTS: https://www.youtube.com/channel/UCTgs... NS2 PROJECTS: https://www.youtube.com/channel/UCS-G... NS3 PROJECTS: https://www.youtube.com/channel/UCBzm... MATLAB PROJECTS: https://www.youtube.com/channel/UCK0Z... VLSI PROJECTS: https://www.youtube.com/channel/UCe0t... IEEE JAVA PROJECTS: https://www.youtube.com/channel/UCSCm... IEEE DOTNET PROJECTS: https://www.youtube.com/channel/UCSCm... APPLICATION PROJECTS: https://www.youtube.com/channel/UCVO9... PHP PROJECTS: https://www.youtube.com/channel/UCVO9... Micans Projects: https://www.youtube.com/user/MICANSIN...
Automatic Generation of Semantic Icon Encodings for Visualizations
 
00:31
Full Title: Automatic Generation of Semantic Icon Encodings for Visualizations Authors: Vidya Setlur, Jock D. Mackinlay Abstract: Authors use icon encodings to indicate the semantics of categorical information in visualizations. The default icon libraries found in visualization tools often do not match the semantics of the data. Users often manually search for or create icons that are more semantically meaningful. This process can hinder the flow of visual analysis, especially when the amount of data is large, leading to a suboptimal user experience. We propose a technique for automatically generating semantically relevant icon encodings for categorical dimensions of data points. The algorithm employs natural language processing in order to find relevant imagery from the Internet. We evaluate our approach on Mechanical Turk by generating large libraries of icons using Tableau Public workbooks that represent real analytical effort by people out in the world. Our results show that the automatic algorithm does nearly as well as the manually created icons, and particularly has higher user satisfaction for larger cardinalities of data. DOI:http://doi.acm.org/10.1145/2556288.2557408
Visualizing Data Using t-SNE
 
55:10
Google Tech Talk June 24, 2013 (more info below) Presented by Laurens van der Maaten, Delft University of Technology, The Netherlands ABSTRACT Visualization techniques are essential tools for every data scientist. Unfortunately, the majority of visualization techniques can only be used to inspect a limited number of variables of interest simultaneously. As a result, these techniques are not suitable for big data that is very high-dimensional. An effective way to visualize high-dimensional data is to represent each data object by a two-dimensional point in such a way that similar objects are represented by nearby points, and that dissimilar objects are represented by distant points. The resulting two-dimensional points can be visualized in a scatter plot. This leads to a map of the data that reveals the underlying structure of the objects, such as the presence of clusters. We present a new technique to embed high-dimensional objects in a two-dimensional map, called t-Distributed Stochastic Neighbor Embedding (t-SNE), that produces substantially better results than alternative techniques. We demonstrate the value of t-SNE in domains such as computer vision and bioinformatics. In addition, we show how to scale up t-SNE to big data sets with millions of objects, and we present an approach to visualize objects of which the similarities are non-metric (such as semantic similarities). This talk describes joint work with Geoffrey Hinton.
Views: 122678 GoogleTechTalks
ADDC 2018 - Cristina Santamarina: Humans vs Bots: Typos, Trolls and other challenges for NLP
 
34:47
Humans vs Bots explores the technical limitations of NLP in a world of high expectations. A mix of faster computers, a more mature artificial intelligence field and the growing collaboration of technologists and humanists is shaping the new generation of conversational interfaces. How much magic is there really involved and where are we in the practice? How are real chatbots from real brands performing? In this talk Cristina Santamarina will review the 10 most important natural language challenges she faces when designing conversational interfaces. From slang and typos to rants and trolls she will provide examples and propose dialogue design techniques that can help mitigate them. More about the talk, authors & slides: https://addconf.com/2018/schedule/humans-vs-bots-typos-trolls-and-other-challenges-for-nlp/ Read about the conference: https://addconf.com
2004-12-08 CERIAS - Using Statistical Analysis to Locate Spam Web Pages
 
36:20
Recorded: 12/08/2004 CERIAS Security Seminar at Purdue University Using Statistical Analysis to Locate Spam Web Pages Dennis Fetterly, Microsoft Commercial web sites are more dependant than ever on being placed prominently within the result pages returned by a search engine to be successful. "Spam" web pages are web pages that are created for the sole purpose of misleading search engines and misdirecting traffic to target sites. Certain classes of spam pages, in particular those that are machine-generated, diverge in some of their properties from the properties of web pages in general. As a result, these pages can be identified through statistical analysis. We have examined a variety of such properties, including linkage structure, page content, and page evolution, and have found that outliers in the statistical distributions of these properties are predominantly caused by web spam. Joint work with Mark Manasse and Marc Najork. Dennis Fetterly is a Technologist in Microsoft Research\'s Silicon Valley lab, which he joined in May, 2003. His research interests include a wide variety of web related topics including web crawling, the evolution and clustering of pages on the web, and identifying spam web pages. (Visit: www.cerias.purude.edu)
Views: 108 ceriaspurdue
The Evolution of End User Programming
 
01:03:22
Google Tech Talk February 1, 2010 ABSTRACT Presented by Allen Cypher, IBM Research Almaden. The popularity of the Web has changed the world of End User Programming. Our research systems can now be built in a web browser that people use in their daily life, semantic information is broadly available, and our users are more experienced and they share their work with others. After twenty-five years of trying to infer the user's intent, Allen will compare early and contemporary end user programming systems to see what progress we have made, and what opportunities we now have for widespread success. Allen Cypher began building systems to automate repetitive activities in 1984. His Eager system was one of the first intelligent agents. In 1993, he edited "Watch What I Do: Programming by Demonstration", which collected the work of earlier pioneers and of the active researchers at the time. In the 90's, he co-developed a visual language called Stagecast Creator that enabled children to create their own games and simulations and publish them on the Web. His current work with CoScripter is aimed at bringing end user programming to the Web.
Views: 15840 GoogleTechTalks
Overview of �Big Data� Research at TU Berlin
 
01:08:06
Intro - By Volker Markl Part 1 - Query Optimization with MapReduce Functions, Kostas Tzoumas Abstract: Many systems for big data analytics employ a data flow programming abstraction to define parallel data processing tasks. In this setting, custom operations expressed as user-defined functions are very common. We address the problem of performing data flow optimization at this level of abstraction, where the semantics of operators are not known. Traditionally, query optimization is applied to queries with known algebraic semantics. In this work, we find that a handful of properties, rather than a full algebraic specification, suffice to establish reordering conditions for data processing operators. We show that these properties can be accurately estimated for black box operators using a shallow static code analysis pass based on reverse data and control flow analysis over the general-purpose code of their user-defined functions. We design and implement an optimizer for parallel data flows that does not assume knowledge of semantics or algebraic properties of operators. Our evaluation confirms that the optimizer can apply common rewritings such as selection reordering, bushy join order enumeration, and limited forms of aggregation push-down, hence yielding similar rewriting power as modern relational DBMS optimizers. Moreover, it can optimize the operator order of non-relational data flows, a unique feature among today's systems. Part 2 - Spinning Fast Iterative Data Flows, Stephan Ewen Abstract: Parallel data flow systems are a central part of most analytic pipelines for big data. The iterative nature of many analysis and machine learning algorithms, however, is still a challenge for current systems. While certain types of bulk iterative algorithms are supported by novel data flow frameworks, these systems cannot exploit computational dependencies present in many algorithms, such as graph algorithms. As a result, these algorithms are inefficiently executed and have led to specialized systems based on other paradigms, such as message passing or shared memory. We propose a method to integrate "incremental iterations", a form of workset iterations, with parallel data flows. After showing how to integrate bulk iterations into a dataflow system and its optimizer, we present an extension to the programming model for incremental iterations. The extension alleviates for the lack of mutable state in dataflows and allows for exploiting the "sparse computational dependencies" inherent in many iterative algorithms. The evaluation of a prototypical implementation shows that those aspects lead to up to two orders of magnitude speedup in algorithm runtime, when exploited. In our experiments, the improved dataflow system is highly competitive with specialized systems while maintaining a transparent and unified data flow abstraction. Part 3 - A Taxonomy of Platforms for Analytics on Big Data, Thomas Bodner Abstract: Within the past few years, industrial and academic organizations designed a wealth of systems for data-intensive analytics including MapReduce, SCOPE/Dryad, ASTERIX, Stratosphere, Spark, and many others. These systems are being applied to new applications from diverse domains other than (traditional) relational OLAP, making it difficult to understand the tradeoffs between them and the workloads for which they were built. We present a taxonomy of existing system stacks based on their architectural components and the design choices made related to data processing and programmability to sort this space. We further demonstrate a web repository for sharing Big Data analytics platform information and use cases. The repository enables researchers and practitioners to store and retrieve data and queries for their use case, and to easily reproduce experiments from others on different platforms, simplifying comparisons.
Views: 383 Microsoft Research
Constructing ontology from experience of interaction
 
08:05
IDEAL MOOC: http://liris.cnrs.fr/ideal/mooc/ External links: - E-puck Experiment http://youtu.be/t1RO5S4mBEY - Little Loop Experiment http://youtu.be/LVZ0cPpmSu8
Views: 443 Olivier georgeon
“Facebook Doesn’t Sell Your Data. It Sells You”: Zeynep Tufekci on How Company’s Profit Really Works
 
16:51
https://democracynow.org - Facebook CEO Mark Zuckerberg faced off with lawmakers in a marathon 5-hour hearing Tuesday about how the voter-profiling company Cambridge Analytica harvested the data of more than 87 million Facebook users, without their permission, in efforts to sway voters to support President Donald Trump. We speak with Zeynep Tufekci, associate professor of information and library science at the University of North Carolina at Chapel Hill. She is also a faculty associate at the Harvard Berkman Klein Center for Internet & Society. Her book is titled “Twitter and Tear Gas: The Power and Fragility of Networked Protest.” Democracy Now! is an independent global news hour that airs weekdays on nearly 1,400 TV and radio stations Monday through Friday. Watch our livestream 8-9AM ET: https://democracynow.org Please consider supporting independent media by making a donation to Democracy Now! today: https://democracynow.org/donate FOLLOW DEMOCRACY NOW! ONLINE: Facebook: http://facebook.com/democracynow Twitter: https://twitter.com/democracynow YouTube: http://youtube.com/democracynow SoundCloud: http://soundcloud.com/democracynow Daily Email: https://democracynow.org/subscribe Google+: https://plus.google.com/+DemocracyNow Instagram: http://instagram.com/democracynow Tumblr: http://democracynow.tumblr.com Pinterest: http://pinterest.com/democracynow iTunes: https://itunes.apple.com/podcast/democracy-now!-audio/id73802554 TuneIn: http://tunein.com/radio/Democracy-Now-p90/ Stitcher Radio: http://www.stitcher.com/podcast/democracy-now
Views: 16684 Democracy Now!
The Potential for Personalization in Web Search - Susan Dumais - ISR Seminar
 
01:02:32
ISR Seminar Susan Dumais Distinguished Scientist, Deputy Managing Director Microsoft Research Lab Friday, September 30, 2016 Title: The Potential for Personalization in Web Search Traditionally search engines have returned the same results to everyone who asks the same question. However, using a single ranking for everyone in every context at every point in time limits how well a search engine can do in providing relevant information. In this talk I outline a framework to quantify the "potential for personalization” which we use to characterize the extent to which different people have different intents for a query. I describe several examples of how we represent and use different kinds of contextual features to improve search quality for individuals and groups. Finally, I conclude by highlighting important challenges in developing personalized systems at Web scale including privacy, transparency, serendipity, and evaluation. Bio: Susan Dumais a Distinguished Scientist at Microsoft, Deputy Managing Director of the Microsoft Research Lab in Redmond, and an adjunct professor in the Information School at the University of Washington. Prior to joining Microsoft, she was at Bell Labs, where she worked on Latent Semantic Analysis, techniques for combining search and navigation, and organizational impacts of new technology. Her current research focuses on user modeling and personalization, context and search, and temporal dynamics of information. She has worked closely with several Microsoft groups (Bing, Windows Desktop Search, SharePoint, and Office Online Help) on search-related innovations. Susan has published widely in the fields of information science, human-computer interaction and cognitive science, and holds several patents on novel retrieval algorithms and interfaces. She is Past-Chair of ACM's Special Interest Group in Information Retrieval (SIGIR), and serves on several editorial boards, technical program committees, and government panels. She was elected to the CHI Academy in 2005, an ACM Fellow in 2006, received the SIGIR Gerard Salton Award for Lifetime Achievement in 2009, was elected to the National Academy of Engineering (NAE) in 2011, received the ACM Athena Lecturer and Tony Kent Strix Awards in 2014, was elected to the American Academy of Arts and Sciences (AAAS) in 2015, and received the Lifetime Achievement Award from Indiana University Department of Psychological and Brain Science in 2016.
Views: 212 UCIBrenICS
NIPS 2011 Learning Semantics Workshop: Towards More Human-like Machine Learning of Word Meanings
 
41:22
Learning Semantics Workshop at NIPS 2011 Invited Talk: Towards More Human-like Machine Learning of Word Meanings by Josh Tenenbaum Josh Tenenbaum is a Professor in the Department of Brain and Cognitive Sciences at Massachusetts Institute of Technology. Him and his colleagues in the Computational Cognitive Science group study one of the most basic and distinctively human aspects of cognition: the ability to learn so much about the world, rapidly and flexibly. Abstract: How can we build machines that learn the meanings of words more like the way that human children do? I will talk about several challenges and how we are beginning to address them using sophisticated probabilistic models. Children can learn words from minimal data, often just one or a few positive examples (one-shot learning). Children learn to learn: they acquire powerful inductive biases for new word meanings in the course of learning their first words. Children can learn words for abstract concepts or types of concepts that have no little or no direct perceptual correlate. Children's language can be highly context-sensitive, with parameters of word meaning that must be computed anew for each context rather than simply stored. Children learn function words: words whose meanings are expressed purely in how they compose with the meanings of other words. Children learn whole systems of words together, in mutually constraining ways, such as color terms, number words, or spatial prepositions. Children learn word meanings that not only describe the world but can be used for reasoning, including causal and counterfactual reasoning. Bayesian learning defined over appropriately structured representations — hierarchical probabilistic models, generative process models, and compositional probabilistic languages — provides a basis for beginning to address these challenges.
Views: 2538 GoogleTechTalks
100 COOL THINGS IN PYTHON (PART 1) - CS50 on Twitch, EP. 14
 
03:14:03
Join CS50's head course assistant, Veronica Nutting, for a tour of some of Python's cool features (with an eventual goal of reaching 100 over several parts!), from data structures to analyzing presidential data. Co-hosted by Colton Ogden. Join us live at twitch.tv/cs50tv and be a part of the live chat every week. This is CS50 on Twitch.
Views: 4334 CS50
Maryann Martone - Where do we go from here? (databases and ontologies)
 
01:26:01
Maryann Martone, University of California, San Diego, USA INCF Short Course "Introduction to Neuroinformatics", September 2012. Munich, Germany http://www.incf.org/programs/training-committee/courses/ni-2012 Talk title: Where do we go from here? (databases and ontologies) Neuroanatomist Maryann Martone talks about experiences in data integration and the neurosciences.
Views: 419 INCF
Two-step Cluster Analysis in SPSS
 
11:42
This is a two-step cluster analysis using SPSS. I do this to demonstrate how to explore profiles of responses. These profiles can then be used as a moderator in SEM analyses.
Views: 158261 James Gaskin
A corpus of psychological diseases and their potential causes
 
09:26
Original version is here: http://togotv.dbcls.jp/ja/20160201.html Biomedical Linked Annotation Hackathon (BLAH) 2 was held in DNA Data Bank of Japan, National Institute of Genetics in Mishima, Shizuoka, Japan. On the first day of the Hackathon (16. Nov.), public symposium of the BLAH 2 was held. In this talk, Fabio Rinaldi makes a presentation entitled "A corpus of psychological diseases and their potential causes". (9:26)
Views: 31 togotv
Metrics Before Models  Approaching Data Science Like an Engineer   Wrangle Conference 2016
 
31:59
Qordoba's Head of Data Science Michelle Casbon discusses what Data Science can learn from Engineering, as part of a panel at Wrangle Conference. Qordoba's Head of Data Science Michelle Casbon discusses Machine Learning and Data Science in Natural Language Processing. Qordoba uses Data Science and Machine Learning to analyze text for emotional content. Dr. Casbon's background is in distributed systems, and, as she has a deep interest in languages, she has applied her interest to affect detection. www.qordoba.com
Views: 17 Qordoba
Lecture 1 | Natural Language Processing with Deep Learning
 
01:11:41
Lecture 1 introduces the concept of Natural Language Processing (NLP) and the problems NLP faces today. The concept of representing words as numeric vectors is then introduced, and popular approaches to designing word vectors are discussed. Key phrases: Natural Language Processing. Word Vectors. Singular Value Decomposition. Skip-gram. Continuous Bag of Words (CBOW). Negative Sampling. Hierarchical Softmax. Word2Vec. ------------------------------------------------------------------------------- Natural Language Processing with Deep Learning Instructors: - Chris Manning - Richard Socher Natural language processing (NLP) deals with the key artificial intelligence technology of understanding complex human language communication. This lecture series provides a thorough introduction to the cutting-edge research in deep learning applied to NLP, an approach that has recently obtained very high performance across many different NLP tasks including question answering and machine translation. It emphasizes how to implement, train, debug, visualize, and design neural network models, covering the main technologies of word vectors, feed-forward models, recurrent neural networks, recursive neural networks, convolutional neural networks, and recent models involving a memory component. For additional learning opportunities please visit: http://stanfordonline.stanford.edu/
Interview about TauChain and Agoras with Ohad Asor
 
46:44
www.idni.org questions are listed in a comment below
Views: 3868 IDNI
Kriton Speech: Knowledge Acquisition & Background
 
03:49
A knowledge acquisition dialogue plus a view of the background knowledge on Attention Deficit Hyperactivity disorder. The background knowledge is viewed by use of Protege (Stanford University).
Views: 77 Psychology Network
Intelligent learning: similarity control and knowledge transfer - Vladimir Vapnik
 
01:02:39
Vladimir Vapnik Columbia University March 30, 2015 During last fifty years a strong machine learning theory has been developed. This theory includes: 1. The necessary and sufficient conditions for consistency of learning processes. 2. The bounds on the rate of convergence which in general cannot be improved. 3. The new inductive principle (SRM) which always achieves the smallest risk. 4. The effective algorithms, (such as SVM), that realize consistency property of SRM principle. It looked like general learning theory has been complied: it answered almost all standard questions that is asked in the statistical theory of inference. Meantime, the common observation was that human students require much less examples for training than learning machine. Why? The talk is an attempt to answer this question. The answer is that it is because the human students have an Intelligent Teacher and that Teacher-Student interactions are based not only on the brute force methods of function estimation from observations. Speed of learning also based on Teacher-Student interactions which have additional mechanisms that boost learning process. To learn from smaller number of observations learning machine has to use these mechanisms. In the talk I will introduce a model of learning that includes the so called Intelligent Teacher who during a training session supplies a Student with intelligent (privileged) information in contrast to the classical model where a student is given only outcomes yy for events xx. Based on additional privileged information x∗x∗ for event xx two mechanisms of Teacher-Student interactions (special and general) are introduced: 1. The Special Mechanism: To control Student's concept of similarity between training examples. and 2. The General Mechanism: To transfer knowledge that can be obtained in space of privileged information to the desired space of decision rules. Both mechanisms can be considered as special forms of capacity control in the universally consistent SRM inductive principle. Privileged information exists for almost any inference problem and can make a big difference in speed of learning processes. More videos on http://video.ias.edu
Yelawolf - Till It’s Gone (Official Music Video)
 
04:48
iTunes: http://smarturl.it/TillItsgone Sign up for updates: http://smarturl.it/Yelawolf.News Music video by Yelawolf performing Till It’s Gone. (C) 2014 Interscope Records Best of Yelawolf: https://goo.gl/vy7NZQ Subscribe here: https://goo.gl/ynkVDL #Yelawolf #TillItsGone #Vevo #HipHop #OfficialMusicVideo
Views: 90814644 YelawolfVEVO
Fairness in Machine Learning
 
01:20:55
Machine learning is increasingly being adopted by various domains: governments, credit, recruiting, advertising, and many others. Fairness and equality are critical aspects, especially in light of anti-discriminatory laws in these domains. Opaque machine learning models: Awareness and mitigation of biases (inherent and perpetuated) is essential. See more on this video at https://www.microsoft.com/en-us/research/video/fairness-machine-learning/
Views: 1195 Microsoft Research
Concept Map Mining annotation tool
 
00:55
This video shows the Concept Map Mining annotation tool, used to annotate a corpus of essays with their corresponding Concept Maps
Views: 622 Jorge Villalon
Graduate Admissions at Rensselaer Computer Science
 
00:58
Graduate Admissions at Rensselaer Computer Science Since Rensselaer Polytechnic Institute granted its first Ph.D. in Computer Science in 1969, we have stayed in the bleeding edge of PC innovation. At first, the teach of software engineering was in the Department of Mathematical Sciences, however in 1984 Computer Science turned into a free office. Our Department has become extensively throughout the years, both in the quantity of employees and in national notoriety. As of now we have 21 personnel, around 85 graduate understudies, and around 450 undergrad majors. The Department is a fantastic domain for graduate understudy preparing - it offers: Great research with a minimum amount of capable specialists in calculations, manmade brainpower, bioinformatics, computational science and designing, PC representation, PC vision, information mining, database frameworks, machine and computational learning, inescapable processing and systems administration, apply autonomy, security, semantic web, and social and psychological systems. A national notoriety for research that has pulled in over $3.5 million in research allows this year. A globally perceived workforce that incorporates officers of ACM specific vested parties and other expert social orders, for example, SIAM, SPIE, and IEEE, writers of various books, editors of driving diaries, and six champs of the prestigious NSF CAREER grant. Employees who are focused on educating notwithstanding their exploration. An all around outfitted lab with cutting edge specific logical PCs and in addition an expansive number of universally useful workstations. Interdisciplinary research with Rensselaer's divisions of Mathematical Sciences and Electrical, Computer and Systems Engineering- - both positioned among the best in the country, and in addition access to world-class multi-disciplinary focuses. Solid connections with industry that give money related support, "genuine" research issues, and work open doors for our graduates. Accordingly of this noticeable quality, the Department can draw in to a great degree capable graduate understudies. These understudies consistently display papers at gatherings and have won prizes for their work while in master's level college. Various Department understudies have established fruitful PC organizations, including Performance Systems International, MapInfo (now Pitney Bowes Business Insight), STEPTools, Etransmedia, and Vicarious Visions. Youtube channel:https://www.youtube.com/channel/UC-XJcaP6ADa2L3RK2dSAxxg Gmail:[email protected]
Views: 104 Subash roy
Analyzing Big Data with Twitter - Lecture 1 - Intro to course; Twitter basics
 
51:23
http://blogs.ischool.berkeley.edu/i290-abdt-s12/ Course: Information 290. Analyzing Big Data with Twitter School of Information UC Berkeley Lecture 1: August 23, 2012 Course description: How to store, process, analyze and make sense of Big Data is of increasing interest and importance to technology companies, a wide range of industries, and academic institutions. In this course, UC Berkeley professors and Twitter engineers will lecture on the most cutting-edge algorithms and software tools for data analytics as applied to Twitter microblog data. Topics will include applied natural language processing algorithms such as sentiment analysis, large scale anomaly detection, real-time search, information diffusion and outbreak detection, trend detection in social streams, recommendation algorithms, and advanced frameworks for distributed computing. Social science perspectives on analyzing social media will also be covered. This is a hands-on project course in which students are expected to form teams to complete intensive programming and analytics projects using the real-world example of Twitter data and code bases. Engineers from Twitter will help advise student projects, and students will have the option of presenting their final project presentations to an audience of engineers at the headquarters of Twitter in San Francisco (in addition to on campus). Project topics include building on existing infrastructure tools, building Twitter apps, and analyzing Twitter data. Access to data will be provided.
Symposium on Blockchain for Robotic Systems
 
07:48:24
Robotic systems are revolutionizing applications from transportation to health care. However, many of the characteristics that make robots ideal for future applications—such as autonomy, self-learning, and knowledge sharing—also raise concerns about the evolution of the technology. Blockchain, an emerging technology that originated in the digital currency field, shows great potential to make robotic operations more secure, autonomous, flexible, and even profitable, thereby bridging the gap between purely scientific domains and real-world applications. This symposium seeks to move beyond the classical view of robotic systems to advance our understanding about the possibilities and limitations of combining state-of-the art robotic systems with blockchain technology. More information at: https://www.media.mit.edu/events/symposium-on-blockchain-for-robotics/ License: CC-BY-4.0 (https://creativecommons.org/licenses/by-nc/4.0/)
Views: 2180 MIT Media Lab
Qiang Yang: When Transfer Learning Meets Deep Learning
 
01:01:13
Abstract: Deep learning has achieved great success as evidenced by many challenging applications. However, deep learning developed so far has some inherent limitations. In particular, deep learning is not yet adaptable to different domains and cannot handle small data. In this talk, I will give an overview of how transfer learning can help alleviate these problems. In particular, I will survey some recent progress on integrating deep learning and transfer learning together and show some interesting applications in sentiment analysis, image processing and dialog systems. Bio: Qiang Yang is the head of Computer Science and Engineering Department at Hong Kong University of Science and Technology (HKUST), where he is a New Bright Endowed Chair Professor of Engineering and the founding director of HKUST’s Big Data Institute. His research interest is artificial intelligence, including machine learning, data mining and planning. He is a fellow of AAAI, IEEE, IAPR and AAAS. He received his PhD from the Department of Computer Science at the University of Maryland, College Park in 1989 and had been a faculty member at the University of Waterloo between 1989 and 1995. He was a professor and NSERC Industrial Research Chair at Simon Fraser University in Canada from 1995 to 2001. He had been the founding director of the Huawei's Noah's Ark Research Lab between 2012 and 2015. He was the founding Editor in Chief of the ACM Transactions on Intelligent Systems and Technology (ACM TIST) and the founding Editor in Chief of IEEE Transactions on Big Data (IEEE TBD). He has served as a PC Chair or General Chair of several international conferences, including ACM KDD, IJCAI, RecSys, IUI and ICCBR. In 2017, he received the ACM SIGKDD Distinguished Service Award. He is currently the President of IJCAI and a council member of AAAI.
Views: 526 UMD CS
Alexey Potapov - Extending Universal Intelligence Models with Formal Notion of Representation
 
38:46
Winter Intelligence Oxford - AGI12 - http://agi-conference.org/2012 ==Extending Universal Intelligence Models with Formal Notion of Representation== Abstract. Solomonoff induction is known to be universal, but incomputable. Its approximations, namely, the Minimum Description (or Message) Length (MDL) principles, are adopted in practice in the efficient, but non-universal form. Recent attempts to bridge this gap leaded to development of the Representational MDL principle that originates from formal decomposition of the task of induction. In this paper, possible extension of the RMDL principle in the context of universal intelligence agents is considered, for which introduction of representations is shown to be an unavoidable meta-heuristic and a step toward efficient general intelligence. Hierarchical representations and model optimization with the use of information-theoretic interpretation of the adaptive resonance are also discussed. Key words: Universal Agents, Kolmogorov Complexity, Minimum Description Length Principle, Representations Paper: http://agi-conference.org/2012/wp-content/uploads/2012/12/paper_10.pdf Alexey Potapov, Sergey Rodionov AIDEUS, Russia {potapov,rodionov}@aideus.com http://winterintelligence.org
Analyzing the Privacy of Android Apps
 
53:56
Google Tech Talk June 17, 2015 (click "show more" for more info) Presented by Jason Hong, Carnegie Mellon University ABSTRACT: Many smartphone apps collect sensitive data about people, in a manner that many users find very surprising. How can we help everyday people in understanding the behaviors of their apps? In this talk, Jason Hong presents three things. The first is results of interviews and surveys of app developers, probing their attitudes and behaviors towards privacy. The second is PrivacyGrade.org, a site that combines crowdsourcing and static analysis to analyze the behavior of 1M Android apps. The third is Gort, a tool that combines heuristics, crowdsourcing, and dynamic analysis to help analysts understand the behavior of a given app. Since the original presentation, Android M launched a new permission model that Hong described as "offer[ing] a lot more privacy protection for people, primarily by making it easier to see what data is being requested as it is being used." ABOUT THE SPEAKER: Jason Hong is an associate professor in the Human Computer Interaction Institute at Carnegie Mellon University. He works in the areas of ubiquitous computing and usable privacy and security, and his research has been featured in the New York Times, MIT Tech Review, CBS Morning Show, CNN, Slate, and more. Jason is also a co-founder of Wombat Security Technologies, and has participated on DARPA's Computer Science Study Panel (CS2P), is an Alfred P. Sloan Research Fellow, a Kavli Fellow, a PopTech Science fellow, and currently holds the HCII Career Development fellowship.
Views: 3386 GoogleTechTalks
Classification Accuracy from the Perspective of the User: Real-Time Interaction with ...
 
21:20
Classification Accuracy from the Perspective of the User: Real-Time Interaction with Physiological Computing Stephen H. Fairclough, Alexander J. Karran, Kiel Gilleade CHI '15: ACM Conference on Human Factors in Computing Systems Session: Brain & Physiological Data use for HCI Abstract The accurate classification of psychophysiological data is an important determinant of the quality when interacting with a physiological computing system. Previous research has focused on classification accuracy of psychophysiological data in purely mathematical terms but little is known about how accuracy metrics relate to users' perceptions of accuracy during real-time interaction. A group of 14 participants watched a series of movie trailers and were asked to subjectively indicate their level of interest in a binary high/low fashion. Psychophysiological data (EEG, ECG and SCL) were used to create a binary classification of interest via a Support Vector Machine (SVM) algorithm. After a period of training, participants received real-time feedback from the classification algorithm and perceptions of accuracy were assessed. The purpose of the study was to compare mathematical classification accuracy with the perceived accuracy of the system as experienced by the users. Results indicated that perceived accuracy was subject to a number of psychological biases resulting from expectations, entrainment and development of trust. The F1 score was generally a significant predictor of perceived accuracy. DOI:: http://dx.doi.org/10.1145/2702123.2702454 WEB:: https://chi2015.acm.org/ Recorded at the 33rd Annual ACM Conference on Human Factors in Computing Systems in Seoul, Korea, April 18-23, 2015
Views: 64 ACM SIGCHI
Computers versus Common Sense
 
01:15:18
Google TechTalks May 30, 2006 Douglas Lenat Dr. Douglas Lenat is the President and CEO of Cycorp. Since 1984, he and his team have been constructing, experimenting with, and applying a broad real world knowledge base and reasoning engine, collectively "Cyc". Dr. Lenat was a professor of computer science at Carnegie-Mellon University and at Stanford University. His interest and experience in national security has led him to regularly consult for several U.S. agencies and the White House. ABSTRACT It's way past 2001 now, where the heck is HAL? For several decades now we've had high hopes for computers amplifying our mental abilities not just giving us access to relevant stored information, but...
Views: 9673 Google
"Extracting Social Meaning from Language" - Dan Jurafsky
 
01:25:24
Dan Jurafsky (Stanford University) presents the inaugural Fillmore Lecture at the 2015 LSA Linguistic Institute. John Rickford, the president of the LSA, introduced both Dan Jurafsky and Lily Wong Fillmore. Full title: "Extracting Social Meaning from Language: The Computational Linguistics of Food, Innovation, and Community" Event description: https://lsa2015.uchicago.edu/events/fillmore-lecture-dan-jurafsky-reception Live tweet summary: https://twitter.com/lsa_2017/timelines/627362988127875072 Thanks to Alan Yu and the 2015 Institute staff for recording and sharing this video.
Sebastiano Galazzo at NDR Conference 2018
 
36:31
NDR - The Artificial Intelligence Conference, Iasi, Romania A New Approach to Neural Networks - Sebastiano Galazzo, IT Manager, axélero Passionate about Artificial Intelligence, Sebastiano (@galazzoseba) brings over 15 years of experience in AI and machine learning to his current position as IT manager at axélero. Sebastiano has dedicated the last few years to designing and developing algorithms to tackle the challenges of Natural Language Processing, image recognition and predictive analysis through machine learning. He is a Microsoft MVP and his work in AI has gained commendation in numerous publications and has received several national and international awards.
#bbuzz: Dominik Benz "Bug bites Elephant: Test-driven Quality Assurance..."
 
37:31
Dominik Benz http://berlinbuzzwords.de/sessions/bug-bites-elephant-test-driven-quality-assurance-big-data-application-development Around the currently available large piles of Big Data, there's happening quite a mixed gathering: Business Engineers define which insightswould be precious, Analysts build models, Hadoop programmers tame the flood of data, and Operations people setup machines and networks. It's exactly the interplay of all participants which is central to project success. This setup together with the distributed nature of processing poses new challenges to well-established models of assuring software artifact quality: How can non-programmers define acceptance criteria? How can functionalities be tested which depend on cluster execution, orchestration of, e.g., different hadoop jobs without delaying the development process? Which data selection is suited best for simulating the live environment? How can intermediate results in arbitrary serialization formats be inspected? In this talk, experiences and best practices from approaching these problems in a large-scale log data analysis project will be presented. At 1&1, our team develops hadoop applications which process roughly 1 billion log events (~1 TB) per day. We will give an overview of the hard- and software setup of our quality assurance environment, which includes FitNesse as a wiki-style acceptance testing framework.Starting from a comparison with existing test frameworks like MRUnit, we will explain how we automate the parameterized deployment of our applications, choose test data sampling strategies, perform workflow management and orchestration of jobs / applications, and use Pig for inspection of intermediate results and definition of final acceptance criteria. Our conclusion is that test-driven development in the field of Big Data requires adaption of existing paradigms, but is crucial for maintaining high quality standards for the resulting applications. About the speaker: Dr. Dominik Benz studied Computer Science with minor Psychology at the University of Freiburg, Germany. In his PhD at the Knowledge and Data Engineering Group (University of Kassel) he applied Data Mining and Knowledge Discovery methods to large datasets of Social Web Systems in order to discover emergent semantic structures. Since November 2012 he is working as a Big Data Engineer at Inovex GmbH, focussing on quality-driven development of Hadoop Applications in Business Intelligence contexts.
Apply sentiment analysis successfully to manage marketing campaigns in real time
 
01:03:10
In this age of the Internet and social media, customers want to communicate directly and instantly with the financial institutions they are banking with, with feedback on a bank's activity occurring almost instantaneously. Banks face increasing pressure to analyse customer reactions in campaigns and product launches real time so that they can adjust their actions to market behaviour. Yet traditional method of analysing customer sentiment through surveys and focus groups are expensive and time-consuming. SUBSCRIBE to our channel! Visit our website http://www.theasianbanker.com/ Like us on Facebook https://www.facebook.com/TheAsianBanker Follow us on: Twitter https://twitter.com/theasianbanker LinkedIn https://www.linkedin.com/company/the-asian-banker Instagram https://www.instagram.com/theasianbankerofficial/
Views: 168 theasianbanker
Search engine indexing
 
35:12
Search engine indexing collects, parses, and stores data to facilitate fast and accurate information retrieval. Index design incorporates interdisciplinary concepts from linguistics, cognitive psychology, mathematics, informatics, and computer science. An alternate name for the process in the context of search engines designed to find web pages on the Internet is web indexing. Popular engines focus on the full-text indexing of online, natural language documents. Media types such as video and audio and graphics are also searchable. This video is targeted to blind users. Attribution: Article text available under CC-BY-SA Creative Commons image source in video
Views: 1521 Audiopedia
Image-based Similarity Search
 
03:55
This service provides an image-based similarity search. The only criterion is the similarity of motifs based on characteristics such as colors, textures, shapes and contrasts. The image-based similarity search currently offers access to a growing portfolio of more than 1.2 M digitized works from the Bavarian State Library out of 12 centuries (manuscripts, rare books, maps). These works belong to the absolute core and peak inventory of the cultural heritage of Bavaria and also to the national patrimony. Overall, more than 43 million images are available. It was set up in cooperation with Fraunhofer-Institut für Nachrichtentechnik. https://bildsuche.digitale-sammlungen.de/
Parsing Objects and Scenes in Two and Three Dimensions
 
01:07:23
The Center for Brains, Minds, and Machines: http://cbmm.mit.edu/ Brains, Minds and Machines Seminar Series "Parsing Objects and Scenes in Two- and Three-Dimensions" Speaker: Alan Yuille, Professor - UCLA and co-director of UCLA Center for Cognition, Vision, and Learning Date: May 16, 2014 Location: Singleton Auditorium, MIT Abstract: We continue the series of weekly discussions and reports on each CBMM challenge question describing progress and problems of ongoing work at CBMM. Thrust 5 is focused on models for the CBMM challenge that can answer CBMM challenge questions while being consistent with human behavior and neural data. This talk presents three recent studies on detecting and parsing objects and scenes and discusses how they contribute to the CBMM challenge. We first address the "what?" problem of detecting animals and animal parts (in a newly labelled dataset) and show the advantages of part-sharing (X. Chen et al. 2014). Next, within the same "what?" problem, we describe an approach to parse humans and estimate their three-dimensional structure from single images (C. Chen et al. CVPR 2014). Finally, we describe "psychophysics in the wild" for rapid detection of objects in complex scenes in a newly labelled dataset (Y. Li et al, CVPR 2014). We conclude discussing how these approaches should be extended to meet the CBMM challenge and other efforts at CBMM.
Mod-01 Lec-22 Natural Language Processing and Informational Retrieval
 
46:47
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Views: 3260 nptelhrd
Natural Language Processing to Improve Student Engagement
 
01:06:30
Dr. Rebecca (Becky) Passonneau, Professor at the Penn State School of Electrical Engineering and Computer Science, shares her research on the application of artificial intelligence through natural language processing (NLP) to analyze the content of students' written work. This work has potential to enhance instruction in a number of impactful ways. Dr. Passonneau shares results presented at her recent workshop, Connecting Language, Interaction and Education in Digital Environments (CLIEDE 2017; Supported by NSF, Penn State Teaching and Learning with Technology, and the Waterbury Chair of the Penn State College of Education). To learn more, visit our website: http://edtechnetwork.psu.edu/ To view the slides from this presentation on Slideshare, visit: https://www.slideshare.net/psuedtechnet/natural-language-processing-to-improve-student-engagement-featuring-dr-rebecca-passonneau This video is available in alternative media upon request. Please contact [email protected] with any accessibility requests and we will be happy to assist you.