Video Recordings

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.