Multilingual Neural Semantic Parsing for Low-Resourced Languages

@inproceedings{Xia2021MultilingualNS,
  title={Multilingual Neural Semantic Parsing for Low-Resourced Languages},
  author={Menglin Xia and Emilio Monti},
  booktitle={STARSEM},
  year={2021}
}
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… 

Bootstrapping Multilingual Semantic Parsers using Large Language Models

This work considers the task of multilingual semantic parsing, and demonstrates the effec-tiveness and theexibility offered by large language models (LLMs) for translating English datasets into several languages via few-shot prompting, and provides a comprehensive study of the key design choices that enable effective data translation via prompted LLMs.

Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems

Results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller models, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system are presented.

References

SHOWING 1-10 OF 32 REFERENCES

Multilingual Semantic Parsing And Code-Switching

This paper describes a transfer learning method using crosslingual word embeddings in a sequence-to-sequence model that achieves state-of-the-art accuracy on the NLmaps corpus and observes a consistent improvement for German compared with several baseline domain adaptation techniques.

Bootstrapping a Crosslingual Semantic Parser

Experimental results indicate that MT can approximate training data in a new language for accurate parsing when augmented with paraphrasing through multiple MT engines, and considering when MT is inadequate, it is found that using this approach achieves parsing accuracy within 2% of complete translation using only 50% of training data.

Cross-lingual Language Model Pretraining

This work proposes two methods to learn cross-lingual language models (XLMs): one unsupervised that only relies on monolingual data, and one supervised that leverages parallel data with a new cross-lingsual language model objective.

Neural Architectures for Multilingual Semantic Parsing

This paper trains one multilingual model that is capable of parsing natural language sentences from multiple different languages into their corresponding formal semantic representations and extends an existing sequence-to-tree model to a multi-task learning framework which shares the decoder for generating semantic representations.

Sequence to Sequence Learning with Neural Networks

This paper presents a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure, and finds that reversing the order of the words in all source sentences improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

Cross-lingual Learning of an Open-domain Semantic Parser

We propose a method for learning semantic CCG parsers by projecting annotations via a parallel corpus. The method opens an avenue towards cheaply creating multilingual semantic parsers mapping

Data Recombination for Neural Semantic Parsing

Data recombination improves the accuracy of the RNN model on three semantic parsing datasets, leading to new state-of-the-art performance on the standard GeoQuery dataset for models with comparable supervision.

Universal Language Model Fine-tuning for Text Classification

This work proposes Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning method that can be applied to any task in NLP, and introduces techniques that are key for fine- Tuning a language model.

A Corpus and Semantic Parser for Multilingual Natural Language Querying of OpenStreetMap

We present a corpus of 2,380 natural language queries paired with machine readable formulae that can be executed against world wide geographic data of the OpenStreetMap (OSM) database. We use the

Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling

This paper presents a two-stage method to enable the construction of SRL models for resourcepoor languages by exploiting monolingual SRL and multilingual parallel data and shows that this method outperforms existing methods.