Meta-Learning a Cross-lingual Manifold for Semantic Parsing

  title={Meta-Learning a Cross-lingual Manifold for Semantic Parsing},
  author={Tom Sherborne and Mirella Lapata},
  journal={Transactions of the Association for Computational Linguistics},
Abstract Localizing a semantic parser to support new languages requires effective cross-lingual generalization. Recent work has found success with machine-translation or zero-shot methods, although these approaches can struggle to model how native speakers ask questions. We consider how to effectively leverage minimal annotated examples in new languages for few-shot cross-lingual semantic parsing. We introduce a first-order meta-learning algorithm to train a semantic parser with maximal sample… 

QAmeleon: Multilingual QA with Only 5 Examples

This approach uses a PLM to automatically generate multilingual data upon which QA models are trained, thus avoiding costly annotation and shows that few-shot prompt tuning for data synthesis scales across languages and is a viable alternative to large-scale annotation.

XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing

This work introduces the XRICL framework, which learns to retrieve relevant English exemplars for a given query to construct prompts and effectively leverages large pre-trained language models to outperform existing baselines.



XGLUE: A New Benchmark Datasetfor Cross-lingual Pre-training, Understanding and Generation

A recent cross-lingual pre-trained model Unicoder is extended to cover both understanding and generation tasks, which is evaluated on XGLUE as a strong baseline and the base versions of Multilingual BERT, XLM and XLM-R are evaluated for comparison.

Learning to Generalize: Meta-Learning for Domain Generalization

A novel meta-learning method for domain generalization that trains models with good generalization ability to novel domains and achieves state of the art results on a recent cross-domain image classification benchmark, as well demonstrating its potential on two classic reinforcement learning tasks.

Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data

Experimental results on three multilingual semantic parsing datasets show that data augmentation with TaF reaches accuracies competitive with similar systems which rely on traditional alignment techniques.

On First-Order Meta-Learning Algorithms

A family of algorithms for learning a parameter initialization that can be fine-tuned quickly on a new task, using only first-order derivatives for the meta-learning updates, including Reptile, which works by repeatedly sampling a task, training on it, and moving the initialization towards the trained weights on that task.

End-to-End Slot Alignment and Recognition for Cross-Lingual NLU

This work proposes a novel end-to-end model that learns to align and predict slots in a multilingual NLU system and uses the corpus to explore various cross-lingual transfer methods focusing on the zero-shot setting and leveraging MT for language expansion.

The ATIS Spoken Language Systems Pilot Corpus

This pilot marks the first full-scale attempt to collect a corpus to measure progress in Spoken Language Systems that include both a speech and natural language component and provides guidelines for future efforts.

Zero-Shot Cross-lingual Semantic Parsing

This work proposes a multi-task encoder-decoder model to transfer parsing knowledge to additional languages using only English-logical form paired data and in-domain natural language corpora in each new language.

Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularization

This paper proposes to use the finite differencesfirst-order algorithm to calculate this gradient from dot-product of gradients, al-lowing explicit control on the weightage of this component relative to standard gradients as a regularization tech-nique, leading to more aligned gradients between different batches.

Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing

Extensive experiments show that despite its simplicity, adding Universal Dependency (UD) relations and Universal POS tags (UPOS) as model-agnostic features achieves surprisingly strong improvement on all parsers.

PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models

On the challenging Spider and CoSQL text-to-SQL translation tasks, it is shown that PICARD transforms fine-tuned T5 models with passable performance into state-of-the-art solutions.