Designing Abstract Meaning Representations for Machine Translation

Speaker:
Martha Palmer
Abstract:
Abstract Meaning Representations (AMRs) are rooted, directional and labeled graphs that abstract away from morpho-syntactic idiosyncrasies such as word category (verbs and nouns), word order, and function words (determiners, some prepositions). They also make explicit many implicit semantic and pragmatic relations. Because syntactic idiosyncrasies and different choices about what to make explicit account for many cross-lingual differences, it is worth exploring whether this representation can serve as a useful, minimally divergent transfer layer in machine translation. This talk will present some of the challenges of semantic representations and discuss the contributions AMRs provide over and above other current representation schemes.
Length:
01:04:32
Date:
11/07/2014
views: 752

Images:
Preview of 11a1.jpg
Image 11a1.jpg
Preview of 11a2.jpg
Image 11a2.jpg
Preview of 11a3.jpg
Image 11a3.jpg
Attachments: (video, slides, etc.)
60 MB
213 downloads
50 MB
222 downloads
381 MB
279 downloads