Assessing the Cross-linguistic Utility of Abstract Meaning Representation
Authors:
Open Access
- 1 June 2024
- journal article
- research article
- Published by MIT Press in Computational Linguistics
- Vol. 50 (2) , 419-473
Abstract
Semantic representations capture the meaning of a text. Abstract Meaning Representation (AMR), a type of semantic representation, focuses on predicate-argument structure and abstracts away from surface form. Though AMR was developed initially for English, it has now been adapted to a multitude of languages in the form of non-English annotation schemas, cross-lingual text-to-AMR parsing, and AMR-to-(non-English) text generation. We advance prior work on cross-lingual AMR by thoroughly investigating the amount, types, and causes of differences that appear in AMRs of different languages. Further, we compare how AMR captures meaning in cross-lingual pairs versus strings, and show that AMR graphs are able to draw out fine-grained differences between parallel sentences. We explore three primary research questions: (1) What are the types and causes of differences in parallel AMRs? (2) How can we measure the amount of difference between AMR pairs in different languages? (3) Given that AMR structure is affected by language and exhibits cross-lingual differences, how do cross-lingual AMR pairs compare to string-based representations of cross-lingual sentence pairs? We find that the source language itself does have a measurable impact on AMR structure, and that translation divergences and annotator choices also lead to differences in cross-lingual AMR pairs. We explore the implications of this finding throughout our study, concluding that, although AMR is useful to capture meaning across languages, evaluations need to take into account source language influences if they are to paint an accurate picture of system output, and meaning generally.Keywords
This publication has 73 references indexed in Scilit:
- Contextualized Formula Search Using Math Abstract Meaning Representation | Proceedings of the 31st ACM International Conference on Information & Knowledge Management2022
- Large-scale AMR Corpus with Re-generated Sentences: Domain Adaptive Pre-training on ACL Anthology Corpus2022
- Abstract meaning representation of TurkishNatural Language Engineering, 2022
- Abstract meaning representation for legal documents: an empirical research on a human-annotated datasetArtificial Intelligence and Law, 2021
- Designing a Uniform Meaning Representation for Natural Language ProcessingKI - Künstliche Intelligenz, 2021
- Parsing Indonesian Sentence into Abstract Meaning Representation using Machine Learning Approach2020
- The efficacy of human post-editing for language translation2013
- Cross-language plagiarism detectionLanguage Resources and Evaluation, 2010
- Machine Translation: Interlingual Methods2006
- Interlingual Machine TranslationThe Computer Journal, 1958