paper-with-me

Papers

Meta-Learning a Cross-lingual Manifold for Semantic Parsing

2022-09-26 · Tom Sherborne, Mirella Lapata

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.

📄 PDF Abstract BibTeX arXiv:2209.12577

Code (1)

tomsherborne/xgr 공식 구현

Tasks

Cross-Lingual TransferMachine TranslationMeta-LearningSemantic Parsing

Similar Papers 제목 키워드 기반

Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsing

2024-10-04 · Jeongwoo Kang, Maximin Coavoux, Cédric Lopez, Didier Schwab

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-Learning

Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsing

2021-06-08 · ACL (IWPT) 2021 8 · Sarah Uhrig, Yoalli Rezepka Garcia, Juri Opitz, Anette Frank

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 ParsingNMTSentence

Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing

2021-04-10 · ACL 2022 5 · Anna Langedijk, Verna Dankers, Phillip Lippe, Sander Bos 외

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-Learning

Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing

2023-07-09 · Tom Sherborne, Tom Hosking, Mirella Lapata

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 Parsing

Learning Cross-lingual Distributed Logical Representations for Semantic Parsing

2018-06-14 · ACL 2018 7 · Yanyan Zou, Wei Lu

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