You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@mxnet.apache.org by "Anjishnu (Jira)" <ji...@apache.org> on 2019/11/19 23:51:00 UTC
[jira] [Created] (MXNET-1438) New Loss Functions for Neural
Information Retrieval
Anjishnu created MXNET-1438:
-------------------------------
Summary: New Loss Functions for Neural Information Retrieval
Key: MXNET-1438
URL: https://issues.apache.org/jira/browse/MXNET-1438
Project: Apache MXNet
Issue Type: New Feature
Components: Gluon
Reporter: Anjishnu
Currently MxNet implements only a few loss functions useful for neural information retrieval - in particular the Triplet Loss. In our recent research at Amazon we showed that this loss is not ideal for neural information retrieval settings and devise a new loss function which significantly outperformed Triplet Loss while improving training time by a factor of 10.
Relevant Paper: [https://arxiv.org/abs/1905.12786] (Published at EMNLP 2019 - WNUT)
We would like to implement this as a loss function in Gluon to help any other people working on neural information retrieval systems using MxNet.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@mxnet.apache.org
For additional commands, e-mail: issues-help@mxnet.apache.org