Multilingual Neural Semantic Parsing for Low-Resourced Languages
This work addresses the data imbalance issue in multilingual semantic parsing for low-resourced languages, though it is incremental as it builds on existing translation and transfer learning techniques.
The authors tackled the problem of data scarcity in multilingual semantic parsing by using machine translation to bootstrap training data from English and employing transfer learning from pretrained multilingual encoders. They introduced a new multilingual dataset based on TOP and showed that their method outperforms baselines and state-of-the-art models, achieving a zero-shot performance of 44.9% exact-match accuracy on Italian sentences.
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.