DeepAI AI Chat
Log In Sign Up

A Conditional Generative Matching Model for Multi-lingual Reply Suggestion

by   Budhaditya Deb, et al.

We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior works largely focus on monolingual models, we propose Conditional Generative Matching models (CGM), optimized within a Variational Autoencoder framework to address challenges arising from multi-lingual RS. CGM does so with expressive message conditional priors, mixture densities to enhance multi-lingual data representation, latent alignment for language discrimination, and effective variational optimization techniques for training multi-lingual RS. The enhancements result in performance that exceed competitive baselines in relevance (ROUGE score) by more than 10% on average, and 16% for low resource languages. CGM also shows remarkable improvements in diversity (80%) illustrating its expressiveness in representation of multi-lingual data.


page 7

page 8

page 13

page 14

page 15

page 16


Are All Languages Created Equal in Multilingual BERT?

Multilingual BERT (mBERT) trained on 104 languages has shown surprisingl...

Unsupervised Cross-lingual Representation Learning at Scale

This paper shows that pretraining multilingual language models at scale ...

Sequence-based Multi-lingual Low Resource Speech Recognition

Techniques for multi-lingual and cross-lingual speech recognition can he...

Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages

This paper proposes a framework to address the issue of data scarcity in...

Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages

Scaling multilingual representation learning beyond the hundred most fre...

Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting

Large language models (LLMs) demonstrate impressive multilingual capabil...