Zero-Shot Cross-lingual Semantic Parsing
Recent work in cross-lingual semantic parsing has successfully applied machine translation to localize parsers to new languages. However, these advances assume access to high-quality machine translation systems and word alignment tools. We remove these assumptions and study cross-lingual semantic parsing as a zero-shot problem, without parallel data (i.e., utterance-logical form pairs) for new languages. We propose 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. Our model encourages language-agnostic encodings by jointly optimizing for logical-form generation with auxiliary objectives designed for cross-lingual latent representation alignment. Our parser performs significantly above translation-based baselines and, in some cases, competes with the supervised upper-bound.
Code (1)
Tasks
Cross-Lingual TransferDecoderFormMachine TranslationSemantic ParsingTranslationWord AlignmentSimilar Papers 제목 키워드 기반
Optimal 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 ParsingA survey of cross-lingual features for zero-shot cross-lingual semantic parsing
The availability of corpora to train semantic parsers in English has lead to significant advances in the field. Unfortunately, for languages other than English, annotation is scarce and so are developed parsers. We then …
Cross-Lingual Word EmbeddingsSemantic ParsingWord EmbeddingsFrustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing
The availability of corpora has led to significant advances in training semantic parsers in English. Unfortunately, for languages other than English, annotated data is limited and so is the performance of the developed p…
Cross-Lingual TransferPOSSemantic ParsingZero-Shot Cross-Lingual TransferTranslate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data
While multilingual pretrained language models (LMs) fine-tuned on a single language have shown substantial cross-lingual task transfer capabilities, there is still a wide performance gap in semantic parsing tasks when ta…
Data AugmentationSemantic ParsingCross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing
Recent efforts have aimed to utilize multilingual pretrained language models (mPLMs) to extend semantic parsing (SP) across multiple languages without requiring extensive annotations. However, achieving zero-shot cross-l…
Cross-Lingual TransferData AugmentationSemantic ParsingZero-Shot Cross-Lingual Transfer