Zurück zur vorherigen Seite

Title : Learning, Adapting, and Exploiting Word Representations for Text Analysis and Search

HTL_Navid_Rekabsaz
Tuesday, 01. May 2018 - 12:00 - 13:00

Health Tech Lunch - 01.05.2018, 12h00 - Sierre, Techno-Pôle (Room Maïa)

Presentation by Navid Rekabsaz (IDIAP)

Title : Learning, Adapting, and Exploiting Word Representations for Text Analysis and Search

Abstract

Word representation methods suggest a computational model to capture semantics of language by providing vectors as proxies to the meaning of terms, and have become the cornerstone of several text and language processing tasks. In this talk, I first briefly review the subtleties of various word representation models, followed by introducing the Generalized/Extended Translation Models, two recent methods to exploit the term-term similarities given by word representation models in "classical" Information Retrieval (IR) models. Motivated by the issues of directly using vanilla word representations in IR model (i.e. topic shifting), I then present studies on the exploration of the vector representation space, as well as learning novel word vectors, specifically tailored for document retrieval. Finally, I briefly discuss the interpretability aspect of the word representations, followed by presenting two applications of the introduced methods in financial sentiment analysis, and gender bias detection.

Bio

Navid Rekabsaz is a post-doctoral researcher at the Natural Language Understanding team of the Idiap Research Institute. His research focus is on the intersection of Deep/Representation Learning with Natural Language Processing and Information Retrieval. Before then, he was a research assistance at the IMP lab of the Vienna University of Technology (TU Wien), where he pursued his master and PhD.

​Registration : https://doodle.com/poll/97nhg2i8vfw5bzxf