Category Archives: TAF Track 2

Case Studies

Track 2: Business & Applications – Wednesday 8 November 
13:30 – 14:15

Building Text Analysis Models to Understand & Predict Adverse Events Occurring With FDA-Approved Drugs

Various drugs approved by the FDA have been associated with adverse medical events in patients. These events are reported to the FDA through different sources, including physicians at hospitals and clinics, pharmacists, and patients. Most of these adverse events are documented in texts. However, manual analysis of these texts for root cause are time consuming and produce qualitative results at best. This session shows how building text analysis models in order to understand the themes related to drug adverse events can help us quantitatively understand which adverse events are most common within a cluster of FDA-approved drugs.

Presented by: Qais Hatim

A New Way of Working Graph & Semantics, Text Analytics, & Linked Data

Using case studies of real-world client projects, Smartlogic’s CEO presents, discusses, and demonstrates how post-relational databases, text analytics, AI, semantics, and linked data are delivering rapid returns on investment in data intensive industries. Cases range from predictive analytics and financial risk assessment to compliance, superior superior customer service, and unified enterprise intelligence within industries including banking, life sciences, media, and healthcare. The talk looks at the technology, the opportunity, lessons learned, and the keys to project success.

Presented by: Jeremy Bentley

Search & Text Analytics

Track 2: Business & Applications – Wednesday 8 November 
14:30 – 15:15

Leveraging Text Analytics to Build a Personalized Information Retrieval Environment

To improve the effectiveness of information findability and usability, we are developing a new mechanism to understand users’ interests and predict the information that will be most relevant to their needs. We analyze the technical documents published by members of the workforce and build models that can be used to match user’s requests with the best available content. We utilize an existing hierarchical taxonomy as part of the clustering effort in order to provide preliminary labels for the clusters. The information retrieval environment we are building will not only support retrieval of relevant corporate information upon request, it is designed to proactively notify targeted members of the workforce when relevant information becomes available.

Presented by: Pengchu Zhang

Using Text Analytics, Taxonomy, & Search to Probe Ignorance & Risk

In this talk, Patrick Lambe takes an unconventional look at how text analytics, taxonomies and search can be used in concert to probe areas of ignorance, not just uncover and organize what is already known, via three problem cases from the areas of public health and public transport. We demonstrate how elements of the search and discovery technology stack can be used to detect patterns in the environment to address or mitigate these types of problems.

Presented by: Patrick Lambe

Fake News & Bad Ad Placement

Track 2: Business & Applications – Thursday 9 November 
10:15 – 11:00

News Analytics System

For modern digital enterprises, the key to survival is held by real-time predictive analytics done with heterogeneous data gathered from multiple sources—layered with contextual intelligence. The data is a mix of structured and unstructured data. Establishing contextual relevance requires systems imbued with deep reasoning capabilities that can link relevant pieces of information from within and outside the organization. This talk presents the outlines of a framework that can gather news events in real time, classify them, reason with them, and finally link them to an enterprise information repository and thereby generate alerts or early warnings for subscribed users. The framework is presented through a number of case studies.

Presented by: Lipika Dey

Content Meets Interest – Contextual Ad Targeting by Means of Cognitive Computing

The globally increasing tendency for political populism and media criticism has raised the sensitivity of brands to avoid misplacement of their own campaigns in negative and compromising contexts (bad ads). However, ad targeting is predominantly based on behavioral targeting techniques that heavily rely on (cookie-based) user profiling. The talk showcases a solution for real-time contextual targeting that is exploiting the full power of cognitive computing to match campaigns to online users’ real interests. The approach abandons tracking of any kind of user data and at the same time increases the precision of ad targeting on a real semantic level—beyond what can be achieved with keyword-based methods.

Presented by: Heiko Beier

Case Studies IIā€”Banks & Publishing

Track 2: Business & Applications – Thursday 9 November 
11:15 – 12:00

Text Analytics & KM

The bank as a nonprofit financial cooperative, which acts as the main source of multilateral financing for the execution of projects in Latin-America, intends to provide solutions to development challenges and support in the key areas of the region. The PMR (Project Monitoring Report) and the PCR (Project Completion Report) are two documents that include a section, known as Lessons Learned, which gathers the challenges and lessons learned of each operation. In order to make those lessons more accessible, reusable, and personalized to the several users, a proof of concept using machine learning and natural language processing technologies, was fulfilled. The scope of the proof of concept consisted of the extraction of the documents’ lessons and their corresponding classification. The aim of this talk is to present the insights gained on behalf of technology during the fulfillment of the proof of concept and specifically to present the results of the different classification algorithms.

Presented by: Kyle S. Strand, Daneila Collaguazo

Machine Learning in Practice

In the last 10 years, most of the academic research on entity extraction and content classification has focused on machine learning and complete automation. The latest tools are very precise, but in academic publishing, the use of automatic classification tools is still controversial. Publishers and information managers want the best of both worlds: a clear list of defined, managed keywords for their content and a cost-effective way of implementing the subject tagging. This presentation reviews the current use of machine-learning tools in publishing, both with and without the use of manually curated taxonomies.

Presented by: Michael Upshall

Text Analytics & Taxonomy

Track 2: Business & Applications – Thursday 9 November 
13:00 – 13:45

Bringing It All Together (At Last): Integrating Structured & Unstructured Information With Text Analytics & Ontologies

Organizations are always looking for better ways to integrate their structured (databases and reports) and unstructured (documents and webpages) information. This concept is not new; in fact, it has been the primary information management goal for many years. The difference is that today, the technology to make this happen has matured to the point that this is real. This talk shares real-life examples of how this is done in large repositories using text analytics and ontologies. Session attendees will understand what an ontology is and how it can be merged with text analytics tools to provide better analytics for their data scientists.

Presented by: Zachary R Wahl

Taxonomies & Text Analytics

This presentation discusses two recent projects where enterprise projects have benefited from direct interactions between taxonomies/ ontologies and text analytics. While these are often seen as competing work streams, our recent work continues to build on the idea that complex information-rich projects require both, and that pursuing one while abandoning the other often leads to poor results or project failure.

Presented by: Gary Carlson

New Applications

Track 2: Business & Applications – Thursday 9 November 
14:00 – 14:45

Human-Like Semantic Reasoning

To address the complexity of language ambiguity requires a technology that can read and understand text the way people do. This session explains the concepts behind linguistic analysis, word disambiguation, and semantic reasoning to read and understand content the way people do. It explains the concepts that support a semantic platform, demonstrates a semantic engine, explains how one mobile phone carrier deployed a self-help solution that automatically answered 24,000,000 customer questions annually with 94% precision, and shows a knowledge platform that automatically organizes hundreds of data sources and millions of unstructured documents around multiple corporate taxonomies and entity clusters using dynamically generated metadata in a precise and complete way.

Presented by: Bryan Bell

Breaking Down Silos With Text Analytics

The next phase of how we communicate has already started. Popularized by Siri, Alexa, and the like, natural language interaction (NLI) has achieved commercial Q&A success. For organizations looking to adopt new experiences with their customers, NLI holds promise. But there is a big difference between AI applications—the distinction is the degree to which they are intelligent. This talk examines the considerations for enterprise application of NLI and how to avoid applications that just drive more white noise.

Presented by: Fiona McNeil

Application Issues

Track 2: Business & Applications – Thursday 9 November 
15:00 – 15:45

Leveraging Text Analytics to Build Applications

In the world of scholarly publishing (as well as many other industries— such as KM/information conferences!), meeting organizers are inundated with submissions for inclusions in conference programs. Given a large set of submissions, how can we develop tools to cluster submitted manuscripts into tracks based on topical similarity? This talk describes a project that used a subject taxonomy, NLP, and other text analytics tools as well as a large corpus of documents to construct an application to cluster submitted manuscripts based on topical similarity, including a GUI interface to interact with and analyze the results. This is not intended as a detailed technical talk (no slides of code!), nor is it intended as a product spotlight; the focus is on using known/existing text analytics tools to construct purpose-built applications to solve specific document-centric problems.

Presented by: Robert Kasenchak

Maximizing Analytic Value From Multi-Language Text Feeds

The universe of text analytics is largely constrained to the output of the entire human race. This can and does result in huge, petabyte- scale problems. Technologies for this scalability, computational distribution, deep learning, resolution, and semantic expression are all new within the last 10 years, and their combination is revolutionary. Key to putting all of this together is that the text analytics are performed in the native language of the original text, prior to the inevitable loss of fidelity in machine or human translation. This talk covers a number of use cases including counterterrorism, knowing your customer, border security, disease tracking and detection, and countering fake news and conspiracy theories.

Presented by: Christopher Biow