Cross-lingual Abstract Meaning Representation Parsing
This addresses the lack of AMR resources for non-English languages, enabling cross-lingual semantic parsing, though it is incremental as it builds on existing projection techniques.
The paper tackles the problem of training Abstract Meaning Representation parsers for non-English languages by proposing an annotation projection method using English as source language, achieving promising results for Italian, Spanish, German, and Chinese. It also introduces an evaluation method that uses English gold annotations to assess target language parsers without requiring target language gold data.
Abstract Meaning Representation (AMR) annotation efforts have mostly focused on English. In order to train parsers on other languages, we propose a method based on annotation projection, which involves exploiting annotations in a source language and a parallel corpus of the source language and a target language. Using English as the source language, we show promising results for Italian, Spanish, German and Chinese as target languages. Besides evaluating the target parsers on non-gold datasets, we further propose an evaluation method that exploits the English gold annotations and does not require access to gold annotations for the target languages. This is achieved by inverting the projection process: a new English parser is learned from the target language parser and evaluated on the existing English gold standard.