DeepAI AI Chat
Log In Sign Up

MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation

by   Yongkang Liu, et al.

Building dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such as GPT-3 and T5. The research on zero-shot dialogue generation without cumbersome language models is limited due to lacking corresponding parallel dialogue corpora. In this paper, we propose a simple but effective Multilingual learning framework for Zero-shot Dialogue Generation (dubbed as MulZDG) that can effectively transfer knowledge from an English corpus with large-scale training samples to a non-English corpus with zero samples. Besides, MulZDG can be viewed as a multilingual data augmentation method to improve the performance of the resource-rich language. First, we construct multilingual code-switching dialogue datasets via translation utterances randomly selected from monolingual English datasets. Then we employ MulZDG to train a unified multilingual dialogue model based on the code-switching datasets. The MulZDG can conduct implicit semantic alignment between different languages. Experiments on DailyDialog and DSTC7 datasets demonstrate that MulZDG not only achieve competitive performance under zero-shot case compared to training with sufficient examples but also greatly improve the performance of the source language.


page 1

page 2

page 3

page 4


MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages

Owing to the lack of corpora for low-resource languages, current works o...

Multilingual Coreference Resolution in Multiparty Dialogue

Existing multiparty dialogue datasets for coreference resolution are nas...

Multilingual Transfer Learning for QA Using Translation as Data Augmentation

Prior work on multilingual question answering has mostly focused on usin...

Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension

Comprehending a dialogue requires a model to capture diverse kinds of ke...

A Closer Look at Few-Shot Crosslingual Transfer: Variance, Benchmarks and Baselines

We present a focused study of few-shot crosslingual transfer, a recently...

Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection

Dialogue disentanglement aims to group utterances in a long and multi-pa...

What Language Model to Train if You Have One Million GPU Hours?

The crystallization of modeling methods around the Transformer architect...