02/02/2021

Representing the Unification of Text Featurization using a Context-Free Grammar

Doruk Kilitcioglu, Serdar Kadioglu

Keywords:

Abstract Paper Similar Papers

Abstract: We propose a novel context-free grammar to represent text embeddings in conjunction with their various transformations. We show how this grammar can serve as a unification layer on top of different featurization techniques, and their hybridization thereof. The approach is embodied in an open-source library, called TextWiser, with a high-level user interface to serve researchers and practitioners. The goal of TextWiser is to enable rapid experimentation with various featurization methods and to serve as a building block within AI applications consuming unstructured data. We highlight several key benefits that are desirable especially in industrial settings where rapid experimentation, reusability, reproducibility, and time to market are of great interest. Finally, we showcase a deployed service powered by TextWiser as a proof-of-concept enterprise application.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38951112
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 11:04 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 8:30 
 0
 0
 0
 0
 21:26 
 0
 0
 0
 0
 10:56 
 0
 0
 0
 0
 11:55 
 0
 0
 0
 0
 13:37 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 0
 15:05 
 0
 0
 0
 0
 16:21 
 0
 0
 0
 0
 8:44 
 0
 0
 0
 0
 4:42 
 0
 0
 0
 0
 6:45 
 0
 0
 0
 0
 4:31 
 0
 0
 0
 0
 14:39 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 21:37 
 0
 0
 0
 0
 12:21 
 0
 0
 0
 0
 1:40 
 0
 0
 0
 0
 15:36 
 0
 0
 0
 0
 20:15 
 0
 0
 0
 0
 22:48 
 0
 0
 0
 1
 12:10 
 0
 0
 0
 0
 29:33 
 0
 0
 0
 0
 5:59 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 15:00 
 0
 0
 0
 0
 9:24 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 14:06 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 10:08 
 0
 0
 0
 0
 18:00 
 0
 0
 0
 0
 10:37 
 0
 0
 0
 0
 18:32 
 0
 0
 0
 0
 26:59 
 0
 0
 0
 0
 4:27 
 0
 0
 0
 0
 14:56