Designing a Uniform Meaning Representation for Natural Language Processing

In this paper we present Uniform Meaning Representation (UMR), a meaning representation designed to annotate the semantic content of a text. UMR is primarily based on Abstract Meaning Representation (AMR), an annotation framework initially designed for English, but also draws from other meaning representations. UMR extends AMR to other languages, particularly morphologically complex, low-resource languages. UMR also adds features to AMR that are critical to semantic interpretation and enhances AMR by proposing a companion document-level representation that captures linguistic phenomena such as coreference as well as temporal and modal dependencies that potentially go beyond sentence boundaries.

Vollständige Referenz
BibTeX

Van Gysel, J. E., Vigus, M., Chun, J., Lai, K., Moeller, S., Yao, J., O’Gorman, T., Cowell, A., Croft, W., Huang, C.-R., Hajič, J., Martin, J. H., Oepen, S., Palmer, M., Pustejovsky, J., Vallejos, R. & Xue, N., (2021). Designing a Uniform Meaning Representation for Natural Language Processing. KI - Künstliche Intelligenz: Vol. 35, No. 0. Springer. (S. 343-360). DOI: 10.1007/s13218-021-00722-w

@article{mci/Van Gysel2021,
author = {Van Gysel, Jens E. L. AND Vigus, Meagan AND Chun, Jayeol AND Lai, Kenneth AND Moeller, Sarah AND Yao, Jiarui AND O’Gorman, Tim AND Cowell, Andrew AND Croft, William AND Huang, Chu-Ren AND Hajič, Jan AND Martin, James H. AND Oepen, Stephan AND Palmer, Martha AND Pustejovsky, James AND Vallejos, Rosa AND Xue, Nianwen},
title = {Designing a Uniform Meaning Representation for Natural Language Processing},
journal = {KI - Künstliche Intelligenz},
volume = {35},
number = {0},
year = {2021},
,
pages = { 343-360 } ,
doi = { 10.1007/s13218-021-00722-w }
}

Sollte hier kein Volltext (PDF) verlinkt sein, dann kann es sein, dass dieser aus verschiedenen Gruenden (z.B. Lizenzen oder Copyright) nur in einer anderen Digital Library verfuegbar ist. Versuchen Sie in diesem Fall einen Zugriff ueber die verlinkte DOI: 10.1007/s13218-021-00722-w

Haben Sie fehlerhafte Angaben entdeckt? Sagen Sie uns Bescheid: Feedback abschicken