Meta-Learning a Cross-lingual Manifold for Semantic Parsing
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 efficiency during cross-lingual transfer. Our algorithm uses high-resource languages to train the parser and simultaneously optimizes for cross-lingual generalization for lower-resource languages. Results across six languages on ATIS demonstrate that our combination of generalization steps yields accurate semantic parsers sampling $\le$10% of source training data in each new language. Our approach also trains a competitive model on Spider using English with generalization to Chinese similarly sampling $\le$10% of training data.
Code (1)
Tasks
Cross-Lingual TransferMachine TranslationMeta-LearningSemantic ParsingSimilar Papers 제목 키워드 기반
Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsing
Cross-lingual AMR parsing is the task of predicting AMR graphs in a target language when training data is available only in a source language. Due to the small size of AMR training data and evaluation data, cross-lingual…
AMR ParsingMeta-LearningTranslate, then Parse! A strong baseline for Cross-Lingual AMR Parsing
In cross-lingual Abstract Meaning Representation (AMR) parsing, researchers develop models that project sentences from various languages onto their AMRs to capture their essential semantic structures: given a sentence in…
Abstract Meaning RepresentationAMR ParsingNMTSentenceMeta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the…
Dependency ParsingFew-Shot LearningMeta-LearningOptimal Transport Posterior Alignment for Cross-lingual Semantic Parsing
Cross-lingual semantic parsing transfers parsing capability from a high-resource language (e.g., English) to low-resource languages with scarce training data. Previous work has primarily considered silver-standard data a…
Data AugmentationSemantic ParsingLearning Cross-lingual Distributed Logical Representations for Semantic Parsing
With the development of several multilingual datasets used for semantic parsing, recent research efforts have looked into the problem of learning semantic parsers in a multilingual setup. However, how to improve the perf…
Semantic Parsing