Saved in:
Bibliographic Details
Main Authors: Di, Donglin, Zhang, Weinan, Zhang, Yue, Wang, Fanglin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.18430
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909361898520576
author Di, Donglin
Zhang, Weinan
Zhang, Yue
Wang, Fanglin
author_facet Di, Donglin
Zhang, Weinan
Zhang, Yue
Wang, Fanglin
contents Making use of off-the-shelf resources of resource-rich languages to transfer knowledge for low-resource languages raises much attention recently. The requirements of enabling the model to reach the reliable performance lack well guided, such as the scale of required annotated data or the effective framework. To investigate the first question, we empirically investigate the cost-effectiveness of several methods to train the intent classification and slot-filling models for Indonesia (ID) from scratch by utilizing the English data. Confronting the second challenge, we propose a Bi-Confidence-Frequency Cross-Lingual transfer framework (BiCF), composed by ``BiCF Mixing'', ``Latent Space Refinement'' and ``Joint Decoder'', respectively, to tackle the obstacle of lacking low-resource language dialogue data. Extensive experiments demonstrate our framework performs reliably and cost-efficiently on different scales of manually annotated Indonesian data. We release a large-scale fine-labeled dialogue dataset (ID-WOZ) and ID-BERT of Indonesian for further research.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18430
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch
Di, Donglin
Zhang, Weinan
Zhang, Yue
Wang, Fanglin
Computation and Language
Making use of off-the-shelf resources of resource-rich languages to transfer knowledge for low-resource languages raises much attention recently. The requirements of enabling the model to reach the reliable performance lack well guided, such as the scale of required annotated data or the effective framework. To investigate the first question, we empirically investigate the cost-effectiveness of several methods to train the intent classification and slot-filling models for Indonesia (ID) from scratch by utilizing the English data. Confronting the second challenge, we propose a Bi-Confidence-Frequency Cross-Lingual transfer framework (BiCF), composed by ``BiCF Mixing'', ``Latent Space Refinement'' and ``Joint Decoder'', respectively, to tackle the obstacle of lacking low-resource language dialogue data. Extensive experiments demonstrate our framework performs reliably and cost-efficiently on different scales of manually annotated Indonesian data. We release a large-scale fine-labeled dialogue dataset (ID-WOZ) and ID-BERT of Indonesian for further research.
title Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch
topic Computation and Language
url https://arxiv.org/abs/2410.18430