Cross-lingual Distillation for Text Classification

05/05/2017
by   Ruochen Xu, et al.
0

Cross-lingual text classification(CLTC) is the task of classifying documents written in different languages into the same taxonomy of categories. This paper presents a novel approach to CLTC that builds on model distillation, which adapts and extends a framework originally proposed for model compression. Using soft probabilistic predictions for the documents in a label-rich language as the (induced) supervisory labels in a parallel corpus of documents, we train classifiers successfully for new languages in which labeled training data are not available. An adversarial feature adaptation technique is also applied during the model training to reduce distribution mismatch. We conducted experiments on two benchmark CLTC datasets, treating English as the source language and German, French, Japan and Chinese as the unlabeled target languages. The proposed approach had the advantageous or comparable performance of the other state-of-art methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/31/2019

Funnelling: A New Ensemble Method for Heterogeneous Transfer Learning and its Application to Cross-Lingual Text Classification

Cross-lingual Text Classification (CLC) consists of automatically classi...
research
06/08/2023

T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification

Cross-lingual text classification leverages text classifiers trained in ...
research
11/13/2016

Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence

This paper presents an approach to classify documents in any language in...
research
10/11/2020

Detecting Foodborne Illness Complaints in Multiple Languages Using English Annotations Only

Health departments have been deploying text classification systems for t...
research
10/19/2018

Revisiting Distributional Correspondence Indexing: A Python Reimplementation and New Experiments

This paper introduces PyDCI, a new implementation of Distributional Corr...
research
02/12/2018

Automatic Generation of Language-Independent Features for Cross-Lingual Classification

Many applications require categorization of text documents using predefi...
research
11/29/2022

Compressing Cross-Lingual Multi-Task Models at Qualtrics

Experience management is an emerging business area where organizations f...

Please sign up or login with your details

Forgot password? Click here to reset