Eric Glover Ph.D.

E-mail: eric_rez5@ericglover.com, Web: http://www.ericglover.com/

 

______________________________________________________________________________

Highlights:

 

_      Key designer and implementer of the Natural Language Processing Engine for a search product from Branch Metrics – covering parsing, understanding, ElasticSearch query generation, result scoring and ranking, and vertical-intent detection (7+ verticals) (Branch)

_      Designed and implemented core enhancement to multi-Billion user-identity graph which probabilistically predicts multiple identifiers from the same user through scanning > 1 TB of events daily

_      Designed and lead implementation of a very high performance query parsing library using chart parse and large knowledge base of entity strings. JAVA version averaged 12 microseconds per query; implemented Python prototype that was < 100 microseconds per query. (Quixey)

_      Designed, implemented, and drove product for automated content collection subsystem for a deep-content viewing app. (Quixey)

_      Lead small team to build very high performance Chinese Language Tokenizer, performed better than Alibaba’s expert tokenizer. (Quixey)

_      Designed and lead small team to build very high performance deep-app function generation system that could match queries to the correct deep-app states covering almost a dozen verticals handling complex grammars (leveraging chart parser and grammar matching engine). (Quixey)

_      Designed (implemented Python version, drove JAVA engineering) Query Intent Service that leveraged large-scale knowledge to predict if Quixey would be able to answer a query – in about 100 microseconds. Was limited-deployed with Ask.com mobile for monetization in five verticals.

_      Created multiple relevance features for MLR-based App Search including a machine learned Gaminess (patent filed and issued). (Quixey)

_      Defined DCG guidelines and assisted in the design of the Quixey Relevance Testing system. (Quixey)

_      Introduced and supported use of GBDT (TreeNet) to Quixey for MLR of App Search. Still in use today.

_      Designed and lead engineers to build large scale web crawling (video sites) system – crawled more than 1 Million videos every day across more than a dozen web sites (As CEO of Intelligent Search Solutions).

_      Designed and implemented a large scale system for non-engineers to execute and manage automated web-scale categorization using active learning and Support Vector Machines – ran on Billions of web pages and managed more than 1000 categories. (SearchMe)

_      Designed multi-vertical scoring model allowing combining results from web, video, photo and music – each with different feature sets. (SearchMe)

_      Designed and lead implementation of very high performance query-based person-name detection engine (< 10 microseconds). (ASK.com)

_      Designed and drove engineering effort of an automated smart-answer system based on Wikipedia data that could handle synonyms – covered more than 15% of Ask.com traffic at peak.

_      Lead small team to develop high performance intelligent MetaSearch Engine that incorporated advanced reasoning and real-time result classification. (NEC)

_      Developed automated learning engine to create biased queries to early search engines improving chance of finding useful results. (Dissertation work U of Michigan)

Experience:

Branch Metrics                                                                                            Palo Alto/Redwood City, CA

Principal Scientist                                                                                         July 2016 - Present

Branch is a deep-linking and analytics company that makes it very easy for app-developers to get all the benefits of deep-linking and attribution across platforms (web-browsers, apps, etc…). My work has been across multiple teams including the Persona (large identity graph), Fraud, and Discovery (A search/discovery product for deep-linked content on people’s phones). My primary role includes mentoring of Jr. Data scientists while being a resource for a variety of projects, as well as being hands on developing production code, algorithms, models and systems.

-       Created a new system for enhancing the company’s multi-Billion user persona graph (user identity-graph), based on large scale network traffic analysis. This approach produces an actual probability score of potential pairings of user-identifiers, analyzing TBs of data daily.

-       Primary designer and implementor of the core NLP engine for the Branch Discovery product – multi (7+) vertical search system which accepts plain English queries. Including parsing, understanding, search-query generation (ElasticSearch), vertical-intent detection, and initial result scoring/ranking.

-       Extensive work on modeling and predicting normalized popularity scores based on unnormalized user engagement data. The popularity scores are a unique signal of how popular a given entity is based on the unnormalized engagement that users have with it. This is a state of the art, patented approach that is equivalent of PageRank for mobile. I was part of the small team which built the generic pipeline for mapping arbitrary engagement data to a normalized popularity score – which behaves consistently across apps.

Quixey                                                                                                            Mountain View, CA

Fellow                                                                                                 Aug 2011 – May 2016

Quixey is an app-search and discovery platform company. Known for functional search and deep-app search and app-mining. With major funding from Alibaba and a strong presence in the Chinese market.

_       Founding advisor: Oct 2009 - August 2011

_       Responsible for early development of ML relevance model for app-search

_       Developed app search in English, Korean, Spanish, and assisted in Chinese App Search

_       Significant work on Machine Learning developing many ranking features, and app-to-app similarity technology

_       Early work deep-app-search co-developing early prototype deep-app search

_       Numerous patents (see below)

_       Developed (and prototyped in Python) very high performance knowledge-based query routing engine (sub 1 ms)

_       Designed and lead development of very high performance knowledge-based query parsing tech < 20 microseconds per query

_       Designed and implemented automated content aggregation system that merged data from a variety of web sources into our Screens product

Intelligent Search Solution                                                                         San Francisco, CA

CEO and Co-Founder                                                                                    Sep 2009 - Aug 2011

 

Intelligent Search Solutions was a small angel funded media search company with an interactive Flash-based UI

 

_      Designed and mostly implemented back-end search and personalization engine

o   {C}Including autosuggest, search, ranking, autocorrect (domain-specific)

_      Designed large-scale crawling system that refreshed over 1M videos per day across more than a dozen sites

 

SearchMe                                                                                                       Mountain View, CA

Principal Scientist/Classification Architect                                                    Mar 2007 – July2009

 

SearchMe was a visual multi-media search engine that had its own crawler and auto-categorization technology to real-time disambiguate search queries into over 1000 categories.

_       Web-scale categorization system (CHOCO): Technical lead/primary coder - large-scale categorization system (more than 1000 categories) - run on Billions of documents in days. System included full web-based UI for training, active learning, evaluation, ontology management and automated error checking to aid Search Analysis/contractors.

_       Vertical suggest/query intention mining: Leveraging full document to category matrix, produced a ranked list of "vertical suggestions" in real-time per search.

_       Multimedia blending: Technical lead - project ranked and index multimedia (YouTube, Hulu, Imeem, Flickr and others) content. Solved complex AI problems related to different features from text-web pages. Implemented custom automated feed processing and defined techniques for efficiently discovering appropriate pages to index.

_       Competitive analysis/judgment collection system (TORGO): Technical lead - Internal web-based system for collecting judgments for competitive analysis and MLR training. System included scrapers to pull data from our competitors and caching system, easy to use UI. Flexible design of code and DB schema to rapidly change user-judgment options.

_       MLR feature design and development: Various roles - coding, system design, and formally defining features. Key accomplishments include defining and design specification of XPATH/Perl based system for rapidly (hours) adding totally new features including use of structured data.

_       Near-real time feed processing system ("El Rapido"): Technical lead/primary coder - near-real-time data inclusion from RSS feeds. System included full process from fetching and parsing feeds to indexing and generation of MLR features. Search Quality team managed feeds and options (via Excel). Significant perceived relevance boost - time from initial proposal to live under 3 weeks.

_       Lead projects on automatic page quality, spam, and many relevance (DCG) improvements

_       Presented in board meetings, as well as involved in other business meetings.

 

Ask.com                                                                                                                     Edison, NJ

Research Engineer                                   May 2004 – Feb 2007, Manager Feb 2007 – Mar 2007

 

Ask.com a division of IAC Search & Media is one of the top search engines in the US. Originally known for question answering, it is still a leading mobile search and ads company.

_       Invited presenter at the NATO MMDSS conference in Gazzada, Italy, September 2007

_       At Ask.com, defined and created multiple core search, entity-extraction and classification-related technologies used by millions of users every day

o   Person Name classifier – 3 microseconds

o   Automatic Smart Answers based on Wikipedia – covered more than 15% of total traffic

o   SQL-based Question Answering engine demonstrated answering more than half of human-generated questions in the area of Baseball

_       Lead a team of engineers to develop and implement internal infrastructure products for improved management of structured data, classification, and data mining

NEC Laboratories America                                                                         Princeton, NJ

Research Staff Member                                                                               Nov 2002 – Apr 2004

 

NEC Laboratories America is a premier research institution which is part of NEC Corporation’s global network of corporate R&D Labs. Known for several high profile research efforts in areas including physics, computer science, semiconductors, and biology.

_       Managed a team of several programmers and students to develop a modular enterprise search technology architecture and demonstration system capable of learning new categories in minutes, and performing category-specific search over a variety of (unstructured) data sources.

_       Developed a prototype enterprise search system (Inquirus 2). This system incorporated many new technologies including: rapid category learning (active learning based), advanced feature selection, SVM-based classification, automated query modifications, intelligent resource routing, multiple-source capabilities, automated query expansion, and search strategies

Education:

 

_      BSE Electrical Engineering, Magna Cum Laude from University of Michigan, Ann Arbor, MI

4/1994

_      MSE Electrical Engineering, University of Michigan, Ann Arbor, MI

5/1997

_      Ph.D. Computer Science Engineering, University of Michigan, Ann Arbor, MI (my dissertation)
8/2001

 

Dissertation:

 

Eric J. Glover, Using Extra-Topical User Preferences to Improve Web-Based Metasearch, Ph.D. Dissertation, University of Michigan, 2001. PDF

 

Patents:

 

Filed more than 75 US Utility Patents. Below are a few selected patents from various companies:

NEC:

_      Selective retrieval metasearch engine, 20020165860

_      ISSUED: Inferring hierarchical descriptions of a set of documents, 7,165,024

_      Using web structure for classifying and describing web pages, 20030221163

_      Meta-search engine architecture,        20040143644

_      Systems and methods for improving feature ranking using phrasal compensation and acronym detection, 20050114130

_      Web crawling, 20050125412

_      Systems and methods for determining document relationship and automatic query expansion, 20050154713

 

ASK.COM

_      Systems and methods for predicting if a query is a name, 20070239735

_      System and method for responding to a user reference query, 20070078842

_      Method for targeting World Wide Web content and advertising to a user, 20070038634

 

 

SearchMe:

SYSTEMS AND METHODS FOR PERFORMING A MULTI-STEP CONSTRAINED SEARCH, 20100017388

 

 

Quixey: Issued as of Jan 18, 2019

 

ISSUED PATENTS

Title

1

9,811,327

Full-Text

Dependency-aware transformation of multi-function applications for on-demand execution

2

9,798,531

Full-Text

Dependency-aware transformation of multi-function applications for on-demand execution

3

9,794,284

Full-Text

Application spam detector

4

9,727,648

Full-Text

Time-box constrained searching in a distributed search system

5

9,659,100

Full-Text

Searching and accessing software application functionality using concepts

6

9,619,574

Full-Text

Searching and accessing software application functionality

7

9,614,683

Full-Text

Signed application cards

8

9,613,221

Full-Text

Signed application cards

9

9,600,530

Full-Text

Updating a search index used to facilitate application searches

10

9,552,414

Full-Text

Dynamic filtering in application search

11

9,471,624

Full-Text

Method for recommending applications for deletion

12

9,432,395

Full-Text

Application spam detector

13

9,405,838

Full-Text

Determining an active persona of a user device

14

9,384,357

Full-Text

Providing application privacy information

15

9,330,186

Full-Text

Similarity engine for facilitating re-creation of an application collection of a source computing device on a destination computing device

16

9,152,674

Full-Text

Performing application searches

17

9,032,392

Full-Text

Similarity engine for facilitating re-creation of an application collection of a source computing device on a destination computing device

Filed Patents at Quixey: http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=0&f=S&l=50&TERM1=glover&FIELD1=IN&co1=AND&TERM2=quixey&FIELD2=AANM&d=PG01

 

 

Branch:

            Multiple filed and provisional patents related to large-scale identity graphs, deeplink ranking, automatic keyword generation for apps, popularity feature generation, and search and understanding for deeplink search systems. None yet published.

 

Personal: Filed provisional patent related to location of mobile devices such as headsets or phones with a nearly dead battery


Publications:

 

Halim Abbas  Ford Garberson  Eric Glover  Dennis P Wall, Machine learning approach for early detection of autism by combining questionnaire and home video screening, Journal of the American Medical Informatics Association, Volume 25, Issue 8, 1 August 2018, Pages 1000–1007, https://doi.org/10.1093/jamia/ocy039

Eric Glover, The "Real World" Web Search Problem, MMDSS NATO Conference, Gazzada, Italy, September 2007. Video Presentation. Please e-mail for an electronic copy of the actual paper.

Eric J. Glover, David M. Pennock, Steve Lawrence, and Robert Krovetz. Inferring hierarchical descriptions, Proceedings of the Eleventh International Conference on Information and Knowledge Management (CIKM'02), November 2002. PS

David M. Pennock, Sandip Debnath, Eric J. Glover, and C. Lee Giles. Modeling information incorporation in markets with application to detecting and explaining events, Proceedings of the 18th Conference on Uncertainty in Artificial Intelligence (UAI-2002), pp. 405-413, August 2002. PS | PDF

Eric J. Glover, Kostas Tsioutsiouliklis, Steve Lawrence, David M. Pennock, and Gary W. Flake. Using web structure for classifying and describing web pages, Proceedings of the Eleventh International World Wide Web Conference, pp. 562-569, May 2002. PS | PDF | HTML

Gary Flake, Eric Glover, Steve Lawrence, C. Lee Giles Extracting Query Modifications from Nonlinear SVMs , Proceedings of the Eleventh International World Wide Web Conference, May 2002. HTML PS.Z PS.gz PS PDF BibTeX ©

David M. Pennock, Gary W. Flake, Steve Lawrence, Eric J. Glover, and C. Lee Giles. Winners don't take all: Characterizing the competition for links on the web, Proceedings of the National Academy of Sciences (PNAS), Volume 99, Issue 8, pp. 5207-5211, April 2002. PS | PDF | abstract | HTML | more info

Steve Lawrence, David M. Pennock, Gary William Flake, Robert Krovetz, Frans M. Coetzee, Eric Glover, Finn Årup Nielsen, Andries Kruger, and C. Lee Giles. Persistence of web references in scientific research. Computer, 34(2): 26-31, 2001 PS | PDF

Steve Lawrence, Frans Coetzee, Eric Glover, David Pennock, Gary Flake, Finn Nielsen, Robert Krovetz, Andries Kruger, and C. Lee Giles.  Persistence of Web References in Scientific Research, IEEE Computer, vol 34, no 2, pp 26--31, 2001

Eric J. Glover, Gary W. Flake, Steve Lawrence, William P. Birmingham, Andries Kruger, C. Lee Giles, David M. Pennock. Improving Category Specific Web Search by Learning Query Modifications, Symposium on Applications and the Internet, SAINT 2001, San Diego, California, January 8--12, 2001.

Frans Coetzee, Eric Glover, Steve Lawrence, and C. Lee Giles. Feature selection in web applications using ROC inflections. In Symposium on Applications and the Internet, SAINT, San Diego, CA, January 8--12 2001.

Andries Kruger, C. Lee Giles, Frans Coetzee, Eric Glover, Gary Flake, Steve Lawrence, and Cristian Omlin. DEADLINER: Building a new niche search engine. In Ninth International Conference on Information and Knowledge Management, CIKM 2000, Washington, DC, November 6-- 11 2000.

Eric J. Glover, Steve Lawrence, Michael D. Gordon, William P. Birmingham, C. Lee Giles, "Web Search -- Your Way," Accepted to Communications of the ACM

Eric J. Glover, Steve Lawrence, William P. Birmingham, C. Lee Giles, "Architecture of a Metasearch Engine that Supports User Information Needs," Eighth International Conference on Information and Knowledge Management (CIKM 99), Kansas City, MO, November, 1999

Eric J. Glover, Steve Lawrence, Michael D. Gordon, William P. Birmingham, C. Lee Giles, "Recommending Web Documents Based on User Preferences," in ACM SIGIR 99 Workshop on Recommender Systems, Berkeley, CA, August, 1999

E. J. Glover, S.R. Lawrence, K.D. Bollacker, C.L. Giles, W.P. Birmingham, G.W. Flake, "A Metasearch Engine Architecture That Supports Individual Information Needs," NEC Research Institute Technical Report, TR# 99-063, May 13, 1999

E. J. Glover, W. P. Birmingham, and M. D. Gordon, "Improving Web Search Using Utility Theory," in Proceedings of the First International Workshop on Web Information and Data Management, WIDM 98. Bethesda, Maryland, 1998

Eric J. Glover, Sunju Park, Anil Arora, Daniel Kiskis and Edmund Durfee, "A case study on the evolution of software tools selection and development in a large-scale multi-agent system," in Workshop on Software Tools for Developing Agents, AAAI 1998. Madison, WI: AAAI

E. J. Glover and W. P. Birmingham, "Using Decision Theory To Order Documents," in Digital Libraries 98, Pittsburgh, PA, 1998: ACM

D. E. Atkins, W. P. Birmingham, E. H. Durfee, E. J. Glover, T. Mullen, E. A. Rundensteiner, E. Soloway, J. M. Vidal, R. Wallace, and M. P. Wellman, "Toward Inquiry-Based Education Through Interacting Software Agents," IEEE Computer, vol. 29, pp. 69-76, 1996