The UdeM-McGill-MITACS machine learning seminar series is continuing its fall schedule. <b>Friday</b>&#39;s seminar:<br><br><meta charset="utf-8"><span class="Apple-style-span" style="font-family: arial, sans-serif; font-size: 13px; border-collapse: collapse; ">Tale of a Neural Network: From Part-Of-Speech to Parsing.<br>

</span><br>by Ronan Collobert<br>NEC Labs<br><br>Location: Pavillon André-Aisenstadt (UdeM), room AA-3195<br>Time: <b>Friday, October 29, 14:30</b><br><br>Abstract: <meta charset="utf-8"><span class="Apple-style-span" style="font-family: arial, sans-serif; font-size: 13px; border-collapse: collapse; ">We will present a single architecture which excels in performance on various Natural Language Processing (NLP) tasks. Instead of hand-crafting task-specific features, generic word representations are <i>learnt</i> from large unlabeled corpuses. We will demonstrate how our architecture naturally applies to a wide range of tasks, from simple tasks like Part-Of-Speech, to complex tasks like Parsing. Analysis and comparison with existing NLP approaches will be given. The presentation will end with the introduction of a simple standalone software, implementing all these tasks with blazing execution speed.<br>

</span>