DeepAI AI Chat
Log In Sign Up

Tuplemax Loss for Language Identification

by   Li Wan, et al.

In many scenarios of a language identification task, the user will specify a small set of languages which he/she can speak instead of a large set of all possible languages. We want to model such prior knowledge into the way we train our neural networks, by replacing the commonly used softmax loss function with a novel loss function named tuplemax loss. As a matter of fact, a typical language identification system launched in North America has about 95 who could speak no more than two languages. Using the tuplemax loss, our system achieved a 2.33 3.85


LanideNN: Multilingual Language Identification on Character Window

In language identification, a common first step in natural language proc...

Automatic Language Identification System for Hindi and Magahi

Language identification has become a prerequisite for all kinds of autom...

Language Identification for Austronesian Languages

This paper provides language identification models for low- and under-re...

LossPlot: A Better Way to Visualize Loss Landscapes

Investigations into the loss landscapes of deep neural networks are ofte...

Open-Set Language Identification

We present the first open-set language identification experiments using ...

Vehicle Re-identification Based on Dual Distance Center Loss

Recently, deep learning has been widely used in the field of vehicle re-...

AfroLID: A Neural Language Identification Tool for African Languages

Language identification (LID) is a crucial precursor for NLP, especially...