Archive for the 'AI' Category
July 16th, 2017, by Tim Finin, posted in Data Science, Machine Learning, NLP, Semantic Web
Deep Representation of Lyrical Style and Semantics for Music Recommendation
Abhay L. Kashyap
11:00-1:00 Thursday, 20 July 2017, ITE 346
In the age of music streaming, the need for effective recommendations is important for music discovery and a personalized user experience. Collaborative filtering based recommenders suffer from popularity bias and cold-start which is commonly mitigated by content features. For music, research in content based methods have mainly been focused in the acoustic domain while lyrical content has received little attention. Lyrics contain information about a song’s topic and sentiment that cannot be easily extracted from the audio. This is especially important for lyrics-centric genres like Rap, which was the most streamed genre in 2016. The goal of this dissertation is to explore and evaluate different lyrical content features that could be useful for content, context and emotion based models for music recommendation systems.
With Rap as the primary use case, this dissertation focuses on featurizing two main aspects of lyrics; its artistic style of composition and its semantic content. For lyrical style, a suite of high level rhyme density features are extracted in addition to literary features like the use of figurative language, profanity and vocabulary strength. In contrast to these engineered features, Convolutional Neural Networks (CNN) are used to automatically learn rhyme patterns and other relevant features. For semantics, lyrics are represented using both traditional IR techniques and the more recent neural embedding methods.
These lyrical features are evaluated for artist identification and compared with artist and song similarity measures from a real-world collaborative filtering based recommendation system from Last.fm. It is shown that both rhyme and literary features serve as strong indicators to characterize artists with feature learning methods like CNNs achieving comparable results. For artist and song similarity, a strong relationship was observed between these features and the way users consume music while neural embedding methods significantly outperformed LSA. Finally, this work is accompanied by a web-application, Rapalytics.com, that is dedicated to visualizing all these lyrical features and has been featured on a number of media outlets, most notably, Vox, attn: and Metro.
Committee: Drs. Tim Finin (chair), Anupam Joshi, Tim Oates, Cynthia Matuszek and Pranam Kolari (Walmart Labs)
July 12th, 2017, by Tim Finin, posted in AI, Machine Learning, Semantic Web
Analysis of Irregular Event Sequences using Deep Learning, Reinforcement Learning, and Visualization
11:00-1:00 Thursday 13 July 2017, ITE 346, UMBC
History is nothing but a catalogued series of events organized into data. Amazon, the largest online retailer in the world, processes over 2,000 orders per minute. Orders come from customers on a recurring basis through subscriptions or as one-off spontaneous purchases, resulting in each customer exhibiting their own behavioral pattern when it comes to the way in which they place orders throughout the year. For a company such as Amazon, that generates over $130 billion of revenue each year, understanding and uncovering the hidden patterns and trends within this data is paramount in improving the efficiency of their infrastructure ranging from the management of the inventory within their warehouses, distribution of their labor force, and preparation of their online systems for the load of users. With the ever increasingly availability of big data, problems such as these are no longer limited to large corporations but are experienced across a wide range of domains and faced by analysts and researchers each and every day.
While many event analysis and time series tools have been developed for the purpose of analyzing such datasets, most approaches tend to target clean and evenly spaced data. When faced with noisy or irregular data, it has been recommended to undergo a pre-processing step of converting and transforming the data into being regular. This transformation technique arguably interferes on a fundamental level as to how the data is represented, and may irrevocably bias the way in which results are obtained. Therefore, operating on raw data, in its noisy natural form, is necessary to ensure that the insights gathered through analysis are accurate and valid.
In this dissertation novel approaches are presented for analyzing irregular event sequences using a variety of techniques ranging from deep learning, reinforcement learning, and visualization. We show how common tasks in event analysis can be performed directly on an irregular event dataset without requiring a transformation that alters the natural representation of the process that the data was captured from. The three tasks that we showcase include: (i) summarization of large event datasets, (ii) modeling the processes that create events, and (iii) predicting future events that will occur.
Committee: Drs. Tim Oates (Chair), Jesus Caban, Penny Rheingans, Jian Chen, Tim Finin
June 27th, 2017, by Tim Finin, posted in Big data, Earth science, Machine Learning, NLP, Ontologies, Semantic Web
Ph.D. Dissertation Defense
Dynamic Data Assimilation for Topic Modeling
9:00am Thursday, 29 June 2017, ITE 325b, UMBC
Understanding how a particular discipline such as climate science evolves over time has received renewed interest. By understanding this evolution, predicting the future direction of that discipline becomes more achievable. Dynamic Topic Modeling (DTM) has been applied to a number of disciplines to model topic evolution as a means to learn how a particular scientific discipline and its underlying concepts are changing. Understanding how a discipline evolves, and its internal and external influences, can be complicated by how the information retrieved over time is integrated. There are different techniques used to integrate sources of information, however, less research has been dedicated to understanding how to integrate these sources over time. The method of data assimilation is commonly used in a number of scientific disciplines to both understand and make predictions of various phenomena, using numerical models and assimilated observational data over time.
In this dissertation, I introduce a novel algorithm for scientific data assimilation, called Dynamic Data Assimilation for Topic Modeling (DDATM), which uses a new cross-domain divergence method (CDDM) and DTM. By using DDATM, observational data in the form of full-text research papers can be assimilated over time starting from an initial model. DDATM can be used as a way to integrate data from multiple sources and, due to its robustness, can exploit the assimilating observational information to better tolerate missing model information. When compared with a DTM model, the assimilated model is shown to have better performance using standard topic modeling measures, including perplexity and topic coherence. The DDATM method is suitable for prediction and results in higher likelihood for subsequent documents. DDATM is able to overcome missing information during the assimilation process when compared with a DTM model. CDDM generalizes as a method that can also bring together multiple disciplines into one cohesive model enabling the identification of related concepts and documents across disciplines and time periods. Finally, grounding the topic modeling process with an ontology improves the quality of the topics and enables a more granular understanding of concept relatedness and cross-domain influence.
The results of this dissertation are demonstrated and evaluated by applying DDATM to 30 years of reports from the Intergovernmental Panel on Climate Change (IPCC) along with more than 150,000 documents that they cite to show the evolution of the physical basis of climate change.
Committee Members: Drs. Tim Finin (co-advisor), Milton Halem (co-advisor), Anupam Joshi, Tim Oates, Cynthia Matuszek, Mark Cane, Rafael Alonso
June 16th, 2017, by Tim Finin, posted in Big data, Data Science, Database, Datamining, KR, Machine Learning, NLP
UMBC Data Science Graduate Programs
UMBC’s Data Science Master’s program prepares students from a wide range of disciplinary backgrounds for careers in data science. In the core courses, students will gain a thorough understanding of data science through classes that highlight machine learning, data analysis, data management, ethical and legal considerations, and more.
Students will develop an in-depth understanding of the basic computing principles behind data science, to include, but not limited to, data ingestion, curation and cleaning and the 4Vs of data science: Volume, Variety, Velocity, Veracity, as well as the implicit 5th V — Value. Through applying principles of data science to the analysis of problems within specific domains expressed through the program pathways, students will gain practical, real world industry relevant experience.
The MPS in Data Science is an industry-recognized credential and the program prepares students with the technical and management skills that they need to succeed in the workplace.
For more information and to apply online, see the Data Science MPS site.
June 15th, 2017, by Tim Finin, posted in Machine Learning, NLP
The topic of this month’s Data Science MD meetup is Getting Started with NLP, Sentiment Analysis and OpenNLP. The meeting will be 6:30-9:00pm, Monday, June 19 in Building 200 Room E100 at the JHU Applied Physics Laboratory. The meeting starts with networking and food and feature talks by two practitioners.
Brian Sacash (Deloitte & Touche): NLP and Sentiment Analysis
Natural Language Processing, the analysis of language, can be challenging if you don’t know where to start. Brian will walk through the Natural Language Tool Kit (NLTK), a Python library built for language analysis, and cover its core functionality. Through live coding he will demonstrate how to build a simple sentiment analysis engine from scratch.
Daniel Russ (NIH): It Takes a Village To Solve A Problem in Data Science
The talk will discuss a scientific case study in data science, computer-based occupational coding of free text job histories taken during epidemiological research studies. Beginning with a rationale for occupational coding, how the coding is performed, and how SOCcer is built on top of Apache OpenNLP. Throughout the talk, I will try to emphasize the importance of working as an interdisciplinary team.
See the meetup announcement to RSVP and get directions and more information.
May 15th, 2017, by Tim Finin, posted in cybersecurity, Machine Learning, NLP, OWL, Semantic Web
Ph.D. Dissertation Proposal
Modeling and Extracting information about Cybersecurity Events from Text
Tuesday, 16 May 2017, ITE 325, UMBC
People rely on the Internet to carry out much of the their daily activities such as banking, ordering food and socializing with their family and friends. The technology facilitates our lives, but also comes with many problems, including cybercrimes, stolen data and identity theft. With the large and increasing number of transaction done every day, the frequency of cybercrime events is also increasing. Since the number of security-related events is too high for manual review and monitoring, we need to train machines to be able to detect and gather data about potential cybersecurity threats. To support machines that can identify and understand threats, we need standard models to store the cybersecurity information and information extraction systems that can collect information to populate the models with data from text.
This dissertation will make two major contributions. The first is to extend our current cyber security ontologies with better models for relevant events, from atomic events like a login attempt, to an extended but related series of events that make up a campaign, to generalized events, such as an increase in denial-of-service attacks originating from a particular region of the world targeted at U.S. financial institutions. The second is the design and implementation of a event extraction system that can extract information about cybersecurity events from text and populated a knowledge graph using our cybersecurity event ontology. We will extend our previous work on event extraction that detected human activity events from news and discussion forums. A new set of features and learning algorithms will be introduced to improve the performance and adapt the system to cybersecurity domain. We believe that this dissertation will be useful for cybersecurity management in the future. It will quickly extract cybersecurity events from text and fill in the event ontology.
Committee: Drs. Tim Finin (chair), Anupam Joshi, Tim Oates and Karuna Joshi
May 15th, 2017, by Tim Finin, posted in AI, Machine Learning, NLP, Paper, Semantic Web
Jennifer Sleeman, Milton Halem, Tim Finin, and Mark Cane, Modeling the Evolution of Climate Change Assessment Research Using Dynamic Topic Models and Cross-Domain Divergence Maps, AAAI Spring Symposium on AI for Social Good, AAAI Press, March, 2017.
Climate change is an important social issue and the subject of much research, both to understand the history of the Earth’s changing climate and to foresee what changes to expect in the future. Approximately every five years starting in 1990 the Intergovernmental Panel on Climate Change (IPCC) publishes a set of reports that cover the current state of climate change research, how this research will impact the world, risks, and approaches to mitigate the effects of climate change. Each report supports its findings with hundreds of thousands of citations to scientific journals and reviews by governmental policy makers. Analyzing trends in the cited documents over the past 30 years provides insights into both an evolving scientific field and the climate change phenomenon itself. Presented in this paper are results of dynamic topic modeling to model the evolution of these climate change reports and their supporting research citations over a 30 year time period. Using this technique shows how the research influences the assessment reports and how trends based on these influences can affect future assessment reports. This is done by calculating cross-domain divergences between the citation domain and the assessment report domain and by clustering documents between domains. This approach could be applied to other social problems with similar structure such as disaster recovery.
May 13th, 2017, by Tim Finin, posted in AI, KR, NLP, Paper, Semantic Web
Sudip Mittal, Aditi Gupta, Karuna Pande Joshi, Claudia Pearce and Anupam Joshi, A Question and Answering System for Management of Cloud Service Level Agreements, IEEE International Conference on Cloud Computing, June 2017.
One of the key challenges faced by consumers is to efficiently manage and monitor the quality of cloud services. To manage service performance, consumers have to validate rules embedded in cloud legal contracts, such as Service Level Agreements (SLA) and Privacy Policies, that are available as text documents. Currently this analysis requires significant time and manual labor and is thus inefficient. We propose a cognitive assistant that can be used to manage cloud legal documents by automatically extracting knowledge (terms, rules, constraints) from them and reasoning over it to validate service performance. In this paper, we present this Question and Answering (Q&A) system that can be used to analyze and obtain information from the SLA documents. We have created a knowledgebase of Cloud SLAs from various providers which forms the underlying repository of our Q&A system. We utilized techniques from natural language processing and semantic web (RDF, SPARQL and Fuseki server) to build our framework. We also present sample queries on how a consumer can compute metrics such as service credit.
March 18th, 2017, by Tim Finin, posted in events, Machine Learning, meetings
A Hands-on Introduction to TensorFlow and Machine Learning
Abhay Kashyap, UMBC ebiquity Lab
10:00-11:00am Tuesday, 28 March 2017, ITE346 ITE325b
As many of you know, TensorFlow is an open source machine learning library by Google which simplifies building and training deep neural networks that can take advantage of computers with GPUs. In this meeting, I will introduce some basic concepts of TensorFlow and machine learning in general. This will be a hands on tutorial where we will sit and code up some basic examples in TensorfFow. Specifically, we will use TensorFlow to implement linear regression, softmax classifiers and feed forward neural networks (MLP). You can find the Python notebooks here. If time permits, we will go over the implementation of the popular word2vec algorithm and introduce LSTMs to build language models.
What you need to know: Python and the basics of linear algebra and matrix operations. While it helps to know basics of machine learning, no prior knowledge will be assumed and there will be a gentle high level introduction to the algorithms we will implement.
What you need to bring: A laptop that has Python and pip installed. Having virtual environments set up on your computer is also a plus. (Warning: Windows-only users might be publicly shamed)
March 17th, 2017, by Tim Finin, posted in AI, KR, NLP, NLP, Ontologies, OWL, RDF, Semantic Web
The Semantics Toolkit
Paul Cuddihy and Justin McHugh
GE Global Research Center, Niskayuna, NY
10:00-11:00 Tuesday, 4 April 2017, ITE 346, UMBC
Paul Cuddihy is a senior computer scientist and software systems architect in AI and Learning Systems at the GE Global Research Center in Niskayuna, NY. He earned an M.S. in Computer Science from Rochester Institute of Technology. The focus of his twenty-year career at GE Research has ranged from machine learning for medical imaging equipment diagnostics, monitoring and diagnostic techniques for commercial aircraft engines, modeling techniques for monitoring seniors living independently in their own homes, to parallel execution of simulation and prediction tasks, and big data ontologies. He is one of the creators of the open source software “Semantics Toolkit” (SemTk) which provides a simplified interface to the semantic tech stack, opening its use to a broader set of users by providing features such as drag-and-drop query generation and data ingestion. Paul has holds over twenty U.S. patents.
Justin McHugh is computer scientist and software systems architect working in the AI and Learning Systems group at GE Global Research in Niskayuna, NY. Justin attended the State University of New York at Albany where he earned an M.S in computer science. He has worked as a systems architect and programmer for large scale reporting, before moving into the research sector. In the six years since, he has worked on complex system integration, Big Data systems and knowledge representation/querying systems. Justin is one of the architects and creators of SemTK (the Semantics Toolkit), a toolkit aimed at making the power of the semantic web stack available to programmers, automation and subject matter experts without their having to be deeply invested in the workings of the Semantic Web.
March 14th, 2017, by Tim Finin, posted in Datamining, Machine Learning, Mobile Computing, Security
Prajit Kumar Das, Anupam Joshi and Tim Finin, App behavioral analysis using system calls, MobiSec: Security, Privacy, and Digital Forensics of Mobile Systems and Networks, IEEE Conference on Computer Communications Workshops, May 2017.
System calls provide an interface to the services made available by an operating system. As a result, any functionality provided by a software application eventually reduces to a set of fixed system calls. Since system calls have been used in literature, to analyze program behavior we made an assumption that analyzing the patterns in calls made by a mobile application would provide us insight into its behavior. In this paper, we present our preliminary study conducted with 534 mobile applications and the system calls made by them. Due to a rising trend of mobile applications providing multiple functionalities, our study concluded, mapping system calls to functional behavior of a mobile application was not straightforward. We use Weka tool and manually annotated application behavior classes and system call features in our experiments to show that using such features achieves mediocre F1-measure at best, for app behavior classification. Thus leading to the conclusion that system calls were not sufficient features for app behavior classification.
March 4th, 2017, by Tim Finin, posted in KR, Ontologies, OWL, RDF, Semantic Web
SADL – Semantic Application Design Language
Dr. Andrew W. Crapo
GE Global Research
10:00 Tuesday, 7 March 2017
The Web Ontology Language (OWL) has gained considerable acceptance over the past decade. Building on prior work in Description Logics, OWL has sufficient expressivity to be useful in many modeling applications. However, its various serializations do not seem intuitive to subject matter experts in many domains of interest to GE. Consequently, we have developed a controlled-English language and development environment that attempts to make OWL plus rules more accessible to those with knowledge to share but limited interest in studying formal representations. The result is the Semantic Application Design Language (SADL). This talk will review the foundational underpinnings of OWL and introduce the SADL constructs meant to capture, validate, and maintain semantic models over their lifecycle.
Dr. Crapo has been part of GE’s Global Research staff for over 35 years. As an Information Scientist he has built performance and diagnostic models of mechanical, chemical, and electrical systems, and has specialized in human-computer interfaces, decision support systems, machine reasoning and learning, and semantic representation and modeling. His work has included a graphical expert system language (GEN-X), a graphical environment for procedural programming (Fuselet Development Environment), and a semantic-model-driven user-interface for decision support systems (ACUITy). Most recently Andy has been active in developing the Semantic Application Design Language (SADL), enabling GE to leverage worldwide advances and emerging standards in semantic technology and bring them to bear on diverse problems from equipment maintenance optimization to information security.