Localizing Open-Ontology QA Semantic Parsers in a Day Using Machine Translation

TL;DR

This paper introduces Semantic Parser Localizer (SPL), a toolkit that rapidly localizes semantic parsers for new languages using neural machine translation, achieving high accuracy in under a day.

Contribution

The paper presents a novel method combining machine translation and few-shot learning to localize semantic parsers for multiple languages efficiently.

Findings

Achieved 61-78% accuracy across new languages and domains.

Outperformed previous state-of-the-art by over 30-40%.

Enabled language localization in less than 24 hours.

Abstract

We propose Semantic Parser Localizer (SPL), a toolkit that leverages Neural Machine Translation (NMT) systems to localize a semantic parser for a new language. Our methodology is to (1) generate training data automatically in the target language by augmenting machine-translated datasets with local entities scraped from public websites, (2) add a few-shot boost of human-translated sentences and train a novel XLMR-LSTM semantic parser, and (3) test the model on natural utterances curated using human translators. We assess the effectiveness of our approach by extending the current capabilities of Schema2QA, a system for English Question Answering (QA) on the open web, to 10 new languages for the restaurants and hotels domains. Our models achieve an overall test accuracy ranging between 61% and 69% for the hotels domain and between 64% and 78% for restaurants domain, which compares favorably to 69% and 80% obtained for English parser trained on gold English data and a few examples from validation set. We show our approach outperforms the previous state-of-the-art methodology by more than 30% for hotels and 40% for restaurants with localized ontologies for the subset of languages tested. Our methodology enables any software developer to add a new language capability to a QA system for a new domain, leveraging machine translation, in less than 24 hours.