DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue

conf_acl(2022)

引用 0|浏览61
暂无评分
摘要
Modern virtual assistants use internal semantic parsing engines to convert user utterances to actionable commands. However, prior work has demonstrated that semantic parsing is a difficult multilingual transfer task with low transfer efficiency compared to other tasks. In global markets such as India and Latin America, this is a critical issue as switching between languages is prevalent for bilingual users. In this work we dramatically improve the zero-shot performance of a multilingual and codeswitched semantic parsing system using two stages of multilingual alignment. First, we show that constrastive alignment pretraining improves both English performance and transfer efficiency. We then introduce a constrained optimization approach for hyperparameter-free adversarial alignment during finetuning. Our Doubly Aligned Multilingual Parser (DAMP) improves mBERT transfer performance by 3x, 6x, and 81x on the Spanglish, Hinglish and Multilingual Task Oriented Parsing benchmarks respectively and outperforms XLM-R and mT5-Large using 3.2x fewer parameters.
更多
查看译文
关键词
multilingual parser,task-oriented
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要