• Query Intent Detection and Event Driven Data Pipeline For Search

    5:45 PM - 6:30 PM: Food/Drink and Networking (Sponsored by Wayfair) 6:30 PM - 6:45 PM: Welcome & Introduction by Mark Canning 6:45 PM - 7:45 PM: Tech Talks: Wayfair engineers will provide an overview of their search stack including a sneak peak into what they are currently working on. Feel free to hangout after the tech talk to interact with the Search team and other attendees. 1. Wayfair’s Query Intent Engine John Castillo from our Search Interpretation team will provide a look Inside Wayfair’s Query Intent Engine. In this talk we will describe how we use NLP, Machine Learning to detect customers intent and provide relevant search results. 2. Event Driven Data Pipeline For Search Suyash Sonawane from our Search Data Pipeline team will share how we are trying to reduce data update latency by building an Event Driven Data Pipeline to transform the way data from multiple sources flows into Wayfair’s search ecosystem. Speakers: Mark Canning, Associate Director of Search John Castillo, Sr. Software Engineer Suyash Sonawane, Sr. Software Engineer Detailed Directions: Public transportation: Orange line to Back Bay or Green line to Copley. There are also limited parking options (http://en.parkopedia.com/parking/back%20bay%20boston/?arriving=201612011900&leaving=201612012100). The Wayfair office is located at 4 Copley Place, above the Copley Place Mall (http://www.simon.com/mall/copley-place/map) (across the bridge from the Prudential Mall). You will see escalators and a sign for "ELEVATORS" in the center of the Copley Place mall (elevators and escalators are both across from the Barneys New York). Proceed up to the Sky Lobby on third floor (SK) and check in with security. Please bring a photo ID. Look for friendly Wayfairians near the elevators and escalators to guide you to the meeting space. Once in the sky lobby, take the elevator or stairs to the second floor. Meetup will be in the Second Floor Large Kitchen area. Thank you to Wayfair for hosting and providing food and drink for our meeting.

  • Haystack - Search Relevance Conference - Charlottesville, VA

    For Informational Purposes Only - RSVP directly with OSC https://haystackconf.com/ This is a conference put on by the people who "wrote the books" on search relevance and open source search technologies. Early bird pricing available through February 28, 2019. Summary from their site: Haystack is the conference for improving search relevance. If you're like us, you work to understand the shiny new tools or dense academic papers out there that promise the moon. Then you puzzle how to apply those insights to your search problem, in your search stack. But the path isn't always easy, and the promised gains don't always materialize. Haystack is the conference for organizations where search, matching, and relevance really matters to the bottom line. For search managers, developers, relevance engineers & data scientists finding ways to innovate, see past the silver bullets, and share what actually has worked well for their unique problems. Please come share and learn! Check out the Haystack 2019 Agenda (https://haystackconf.com/agenda/) for session details.

  • Semantic Search with Apache Solr / Google Cloud Search

    5:30 - 6:00 PM - Food/Drink and Networking (Sponsored by Chewy) Semantic Search with Apache Solr This talk will provide an overview of what Semantic Search is and a brief introduction of how to implement a Semantic search system using the capabilities of Apache Solr. The goal is to create a substantially more relevant search experience for users. Presenter - Amir Noel is a Senior Software Engineer on the search team at Chewy. Google Cloud Search This talk will provide an overview of Google’s latest venture into enterprise search. The nostalgic yellow GSA hardware has now been retired to make way for the best search features that today’s information workers expect and only the cloud can really offer. The presentation will provide details into how companies can adopt the cloud search experience, what features are available today and a look into what Google has in store for the future of search. Presenter - Chris Cook is a Search Sales Engineer with Onix and has over 30 years experience in the Information Technology industry. The past 11 years have been focused specifically around search in the enterprise. He brings with him a vast array of industry knowledge and real-world experience pertaining to technology deployments, networking, security systems, web and cloud computing. Thank you to Chewy for hosting and providing food and drink for our meeting.

  • Auto-complete and Query Classification

    Rakuten USA

    5:30 - 6:00 PM - Food/Drink and Networking (Sponsored by Rakuten) Autocomplete at Rakuten - Keith Thoma Autocomplete or query completion is an important part of a search experience on any website. It is often the first feature users engage with when performing a search. Issues such as bad term suggestions, slow responses, or bad filters can lead to degraded user experience and a decrease in sales for an e-commerce organization. Rakuten has built a solution that can quickly be deployed to various properties across the world. This solution is built using a combination of technologies like: Solr, NLP, Python and ML models. It also includes generating suggestions, cleaning suggestions, suggesting filters and being able to handle public traffic. About the Presenter Keith Thoma is a software engineer at the Rakuten Americas Big Data Department in Boston MA. His primary role is to develop search and data solutions for Rakuten subsidiaries as part of the Americas Big Data team. This includes tasks such as relevancy tuning, NLP, and platform migrations. The team has successfully launched search and data projects in the United States, Brazil, Europe, and Japan. Prior to his work at Rakuten, Keith worked on search projects for companies all over the globe including Dell and European Directories affiliates. Query Classification – Yiu-Chang Lin Query classification has been widely studied to understand users' search intent to improve user satisfaction and e-commerce conversion rates. A query can be associated with a category label that belongs to a taxonomy tree describing the items in the catalog. However, product-related search queries are typically short, ambiguous, and continuously changing depending on seasonal trends and the introduction of new products over time. Moreover, having humans annotate large amount of queries with the proper category label is nearly infeasible in practice. In this talk, we will introduce an unsupervised method that converts millions of users’ browsing behavioral data into automatically labeled data that can be consumed by machine learning models. We also compare and contrast different state-of-the-art text classifiers and demonstrate that an ensemble of linear SVMs achieves the best performance in terms of F-1 score. About the Presenter Yiu-Chang Lin is a research scientist at Rakuten Institute of Technology (RIT) in Boston, MA. Prior to that, he was a graduate research assistant in the School of Computer Science while pursuing an M.S. in Language Technology at Carnegie Mellon University. His research interest lies in the intersection of machine learning and natural language processing. He has been working on numerous e-commerce related projects including query understanding, learning to rank, product linking, etc. Lightning Talk - Al Cole Search platforms like Apache Solr and Elasticsearch can deliver a highly relevant search experience when configured properly for the use case they will be serving. However, there are times when overriding those results makes sense and business rules are a vehicle for accomplishing that goal. In this lightning talk, Al will introduce what business rules are (e.g. triggers and actions) and when they might be appropriate for your use case. About the Presenter Al Cole of NorthRidge Software provides search consulting services and develops insight applications for his clients. https://www.linkedin.com/in/coleal Thank you to Rakuten for hosting and providing food and drink for our meeting.

  • E-commerce Search Technologies / Robotics, Search & AI

    5:30 - 6:00 PM - Food/Drink and Networking (Sponsored by Chewy) Search Technologies at Chewy This talk will provide an overview of Chewy's current Solr search implementation, what they use it for and the scale of their operations. The presentation will include details on how data and machine learning driven insights are driving incremental revenue through search. From a technology standpoint the talk will touch on ML, NLP and distributed computing at scale. Presenter - Karthikeyan Janakiraman is the VP of Software Engineering at Chewy and a technology leader who has built several scalable distributed data driven systems inclusive of search engines, recommendation engines, master data management platforms, operational data stores, data warehouse and data lakes for e-commerce companies. He is passionate about data, machine learning and distributed computing. The Intersection of Robotics, Search and AI with Solr, MyRobotLab, and Deep Learning This talk will present the integration of MyRobotLab and Solr to power the InMoov robot - the world's first life size humanoid 3D printed open source robot. The InMoov robot was designed by french sculptor Gael Langevin and MyRobotLab was started by software developer Greg Perry. This topic incorporates a variety of technology components (e.g. Solr, robotics, vision services and chatbots). Presenter - Kevin Watters is the founder KMW Technology, a professional services organization based in Boston that develops search, analytics and AI applications. He is a contributor to many open source projects including Solr, JavaCV and MyRobotLab. Thank you to Chewy for hosting and providing food and drink for our meeting.

  • Multilingual Search & Chatbots in Healthcare / Solr Time Routed Aliases

    • What we'll do Multilingual Search & Chatbots in Healthcare / Solr Time Routed Aliases 6:30 - 7:00 PM - Food/Drink and Networking Multilingual Search - Kyruus’ Guide to Find a Doctor in Spanish At Kyruus, we believe that every patient has a right to access care. However, most provider searches at hospitals fail to serve a large population: Spanish speakers. Finding the right doctor is challenging enough in English. We want to go even further: delivering great provider search for the 40 million Spanish speakers in the US. We will share how Kyruus is using Elasticsearch to enable a great Spanish search experience by discussing: - How Spanish and English search differ - Features of Elasticsearch that we used to implement Spanish search - How we allow search using Spanish and English medical jargon After hearing this presentation, you will learn tips to better serve Spanish speakers in all search-based applications so that you can start your own multilingual search project. Presenters - Michelle Chen is a Software Engineer on the Search Team at Kyruus in Boston. Her team works directly to provide search, scheduling, and data management solutions that help health systems match patients with the right providers. Michelle earned her B.S. and M.Eng in Computer Science from MIT. Guided Search through Chatbots in Patient Access Management We want to provide a conversational user experience for "ProviderMatch Consumer" users, as an alternative entry point to patient-provider matching (versus the search/filter paradigm). We'll share our experience designing and developing an embedded Chatbot Widget that enables a better patient-provider match by guiding the consumer to narrow down searchers more quickly. Presenters - Members of the Kyruus technical team. Solr 7.3 Time Routed Aliases David & Gus (NEST members) have been working on a new feature in Solr 7.3 called "Time Routed Aliases". With Time Routed Aliases, Solr distributes incoming documents to the right collection for a time interval and will auto create new collections in the alias as newer documents are added. Hear about what scalability problems this feature solves, how it works, and what enhancements are to come. Presenters - David Smiley - Apache Solr Committer and NEST Co-organizer - Gus Heck - Founder, Chief Architect at Needham Software LLC Thank you to Lucidworks for sponsoring the food and drink and Kyruus for providing the meeting space! https://www.google.com/maps/place/222+Berkeley+St,+Boston,+MA+02116/@42.350667,-71.073194,16z/data=!4m5!3m4!1s0x89e37a74ad98b309:0xef6bd60d212b2bd6!8m2!3d42.350667!4d-71.0731944?hl=en-US • What to bring • Important to know Please register for this Meetup using your full name. You can enter the building from the main entrance on Berkeley Street. Proceed to the front desk, to the right side of the building as you enter, to check in - you will need government-issued identification. Once you have checked in, you will use the elevator bay facing the security desk to proceed to the 7th floor.

  • Enterprise Search & Machine Learning

    Black Duck

    5:30 - 6:00 PM - Food/Drink and Networking Enterprise Search Use Case Creating a successful search experience within an enterprise can be a challenging task. To succeed, you must handle multiple content sources managed by different applications with unique data models and document permissions. This talk will discuss the enterprise search use case and highlight the key areas that must be addressed for a successful implementation and deployment. In addition, we will cover business drivers, search architectures, connectors, pipelines, schema design, multi-lingual content, authN/authZ, search applications and more. Presenter Al Cole is currently Director of Consulting at Lucidworks and he also serves as a co-organizer of the New England Search Technologies (NEST) Meetup group. http://www.linkedin.com/in/coleal Machine Learning: The future is here ... Deploying machine learning onto enterprise search required an entire team of data scientists, developers and database experts to manage the complex machine learning algorithms and deploy them in search systems. Until now. New advancements in machine learning are making enterprise search more intelligent – and cost-effective – than ever before by taking the pain out of delivering a more relevant experience for users. This talk will cover how machine learning removes the complexity from managing enterprise search, provides a more effective user experience automatically, and plays a major role in effectively scaling your search practice. Presenters Gauthier Robe, vice president of platform at Coveo™ will explain the technical aspects of machine learning within Coveo™ Machine Learning (Coveo™ ML), and Daniel Cadoch, partner manager at Coveo™, will discuss the journey to relevance with machine learning for companies with the Coveo™ Relevance Maturity Model. https://www.linkedin.com/in/danielcadoch/ Sponsors Thank you to Coveo™ for sponsoring the food and drink and Black Duck Software for providing the meeting space!

  • Flax: Lucene Hackday

    BA Insight

    We're Flax ( http://www.flax.co.uk ), search developers from Cambridge U.K., visiting for Lucene Revolution. A couple of days before the event, we're going to spend a day hacking Lucene and Lucene-based search engines (Solr, Elasticsearch....). BA Insight have very kindly offered us a room for the day - you'll need to bring a laptop but there will be ample power points and web access. We're running a similar event in London the week before (http://www.meetup.com/Apache-Lucene-Solr-London-User-Group/events/233393325/). We don't yet have a plan for what we'll work on - ideas gratefully received! If you know a JIRA issue (https://issues.apache.org/jira/browse/LUCENE) that could do with some work or an entirely new feature we could create do let us know in the comments. We'll have several Lucene committers around to guide us and you'll need some Java experience to get fully involved. Lucidworks (http://www.lucidworks.com) have very kindly offered to sponsor some drinks and sharing plates at MJ O'Connors (http://mjoconnors.com), downstairs from the hackday venue. We'll be there from 6pm (ish).

  • Greetings From Plato’s Cavemen: Search Shadows from a Sitecore Architect

    5:30 - 6:00 PM - Food and Networking Please Note: The location for this meeting has been moved to Monster (133 Boston Post Road, Weston, MA) The meeting will begin with a lightning talk by Vijay Adusumilli (Senior Manager of Software Engineering Technologies) about Search technologies and projects at Monster. After that, Grant Killian will deliver the following presentation to the group. Greetings From Plato’s Cavemen: Search Shadows from a Sitecore Architect Sitecore is a popular content management system increasingly targeting the enterprise market. Search is a critical component of the Sitecore platform. Getting search right can be the difference between a CMS implementation success or failure. Grant will present the search landscape through the eyes of a Sitecore Architect, a caveman interpreting search “shadows” on Plato’s allegorical cave wall. Through the lens of the Sitecore technology stack, Grant will explore the spectrum of search providers and how they apply to this web-based Windows server technology for enterprise content management. This will be a fun, interactive session – when else can you combine Greek philosophy with search scalability? Presenter Grant Killian is a Sitecore Architect for Rackspace Hosting, the #1 managed cloud company. Grant works with global Sitecore CMS implementations on topics of performance, scalability, custom development, and general best practices. Prior to Rackspace, Grant worked at Sitecore as a Solution Architect focusing on enterprise projects. Grant might be a caveman when it comes to search, but he has over 20 years of software development experience, including success as a technical lead for Credit Suisse’s option trading platform in Zürich, Switzerland.