tag:calagator.org,2005:/events/searchCalagator: Events tagged with: embeddings2018-09-26T08:52:07-07:00tag:calagator.org,2005:Calagator::Event/12504743312018-09-26T08:52:07-07:002018-09-26T08:52:07-07:00 Wednesday, October 10, 2018 Peer mentoring, NLP presentation and StarSpace Embedding paper reviewWednesday, October 10, 2018 from 6-8pm at The Tech Academyhttp://calagator.org/events/12504743312018-10-10T18:00:00-07:002018-10-10T20:00:00-07:00<div class="vevent">
<h1 class="summary"> 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">
<a href='/venues/202395971' class='url'>
<span class='fn org'>The Tech Academy</span>
</a>
<div class="adr">
<div class="street-address">310 SW 4th Ave Suite 230</div>
<span class="locality">Portland</span>
, <span class="region">OR</span>
<span class="postal-code">97204</span>
<div class='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>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" href="https://www.meetup.com/Portland-Deep-Learning/events/254853087/">Website</a></li>
</ul>
<div class="tags">
<h3>Tags</h3>
<p><a class="p-category" href="/events/tag/deep leaning">deep leaning</a>, <a class="p-category" href="/events/tag/embeddings">embeddings</a>, <a class="p-category" href="/events/tag/machine learning">machine learning</a>, <a class="p-category" href="/events/tag/natural language processing">natural language processing</a></p>
</div>
<div class='single_view_right'>
<a href='http://calagator.org/events/1250474331.ics'>Download to iCal</a>
<div id='edit_link'>
<p>You can <a href="http://calagator.org/events/1250474331/edit">edit this event</a>.</p>
</div>
<div id='metadata'>
This item was added directly to Calagator <br /><strong>Wednesday, September 26, 2018 at 8:52am</strong>.
</div>
</div>
</div>
45.5209 -122.6747