Multilingual Neural Semantic Parsing for Low-Resourced Languages

06/07/2021
by   Menglin Xia, et al.
9

Multilingual semantic parsing is a cost-effective method that allows a single model to understand different languages. However, researchers face a great imbalance of availability of training data, with English being resource rich, and other languages having much less data. To tackle the data limitation problem, we propose using machine translation to bootstrap multilingual training data from the more abundant English data. To compensate for the data quality of machine translated training data, we utilize transfer learning from pretrained multilingual encoders to further improve the model. To evaluate our multilingual models on human-written sentences as opposed to machine translated ones, we introduce a new multilingual semantic parsing dataset in English, Italian and Japanese based on the Facebook Task Oriented Parsing (TOP) dataset. We show that joint multilingual training with pretrained encoders substantially outperforms our baselines on the TOP dataset and outperforms the state-of-the-art model on the public NLMaps dataset. We also establish a new baseline for zero-shot learning on the TOP dataset. We find that a semantic parser trained only on English data achieves a zero-shot performance of 44.9 exact-match accuracy on Italian sentences.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/03/2022

Crosslingual Generalization through Multitask Finetuning

Multitask prompted finetuning (MTF) has been shown to help large languag...
research
08/07/2021

Multilingual Compositional Wikidata Questions

Semantic parsing allows humans to leverage vast knowledge resources thro...
research
12/15/2022

DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue

Modern virtual assistants use internal semantic parsing engines to conve...
research
04/06/2020

Bootstrapping a Crosslingual Semantic Parser

Datasets for semantic parsing scarcely consider languages other than Eng...
research
12/14/2022

Evaluating Byte and Wordpiece Level Models for Massively Multilingual Semantic Parsing

Token free approaches have been successfully applied to a series of word...
research
05/22/2023

The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning

Multilingual semantic parsing aims to leverage the knowledge from the hi...
research
03/16/2022

Transforming Sequence Tagging Into A Seq2Seq Task

Pretrained, large, generative language models (LMs) have had great succe...

Please sign up or login with your details

Forgot password? Click here to reset