Export to

• Google Calendar
• iCalendar file
• hCalendar markup
  <div class="vevent h-event"> <h1 class="summary p-name"> Wednesday, October 10, 2018 Peer mentoring, NLP presentation and StarSpace Embedding paper review</h1> <div class='date'><time class="dtstart dt-start" title="2018-10-10T18:00:00" datetime="2018-10-10T18:00:00">Wednesday, October 10, 2018 from 6</time>–<time class="dtend dt-end" title="2018-10-10T20:00:00" datetime="2018-10-10T20:00:00">8pm</time></div> <div class="location vcard p-location h-card"> <a class="url" href='http://calagator.org/venues/202395971'><span class='fn org p-name'>The Tech Academy</span></a> <div class="adr p-adr h-adr"> <div class="street-address p-street-address">310 SW 4th Ave Suite 230</div> <span class="locality p-locality">Portland</span> , <span class="region p-region">OR</span> <span class="postal-code p-postal-code">97204</span> <div class="country-name p-country-name">us</div> (<a href='https://maps.google.com/maps?q=310%20SW%204th%20Ave%20Suite%20230,%20Portland%20OR%2097204%20us'>map</a>) </div> </div> <div class="description p-description"> <p>We'll have a short presentation on deep NLP and review the paper "StarSpace: Embed All The Things!"</p> <p>The major vendors in cloud-based services are starting to provide machine learning as a service, such as Google Cloud AutoML Natural Language and Azure Language Understanding (LUIS). Jim Tyhurst will give a brief demonstration of IBM Watson Natural Language Classifier service (<a href="https://www.ibm.com/watson/services/natural-language-classifier/">https://www.ibm.com/watson/services/natural-language-classifier/</a>), which enables you to build a custom classifier with no programming. Just create a new instance and submit training data. When the system has finished training, you can submit a document through a web API. The system responds with JSON, giving a list of some possible categories with a confidence score associated with each category. We will discuss some of the advantages and disadvantages of this service.</p> <p>StarSpace: Embed All The Things! - describes a general-purpose neural embedding model that can solve a wide variety of problems: labeling tasks such as text classification, ranking tasks such as information retrieval/web search, collaborative filtering-based or content-based recommendation, embedding of multi-relational graphs, and learning word, sentence or document level embeddings. <a href="https://arxiv.org/abs/1709.03856">https://arxiv.org/abs/1709.03856</a></p> </div> <h3>Links</h3> <ul> <li><a class="url u-url" href="https://www.meetup.com/Portland-Deep-Learning/events/254853087/">Website</a></li> </ul> </div>