Tense and Aspect Semantics for Sentential AMR

Many English tense and aspect semantic contrasts are not currently captured within Abstract Meaning Representation (AMR) annotations. The proposed framework augments the representation of finite predications in AMR to include a four-way temporal distinction (event time before, up to, at, or after speech time) and several aspectual distinctions (including static vs. dynamic, habitual vs. episodic, and telic vs. atelic). We validate this approach with a small annotation study of sentences from The Little Prince and report details of ongoing discussion to refine the framework. This will enable AMR to be used for NLP tasks and applications that require sophisticated reasoning about time and event structure. The Abstract Meaning Representation (AMR) is a readable and compact framework for broadcoverage semantic annotation of English sentences (Banarescu et al., 2013).1 AMR aims to abstract away from syntactic idiosyncrasies such that sentences with the same basic meaning are represented by the same AMR graph. This paper extends existing AMR to include a coarse-grained representation of tense and aspect. Figure 1 shows a sentence with its annotation from the existing AMR corpus with our proposed additions for tense (in blue) and aspect (in purple). Existing annotation in figure 1 specifies entities and propositional structure2 but notably omits the present time meaning of the copula and the future meaning of “going to.” It also does not specify whether these eventualities3 are stative (temporary http://amr.isi.edu/; data released at https://amr.isi.edu/download/ amr-bank-struct-v1.6.txt (Little Prince) and https://catalog.ldc.upenn.edu/LDC2017T10 This includes both the PropBank frameset last-01 and the AMR-specific frameset be-located-at-91. We understand eventualities to include all kinds of events: states, activities, achievements, accomplishments, and processes. (a / and :op1 (b / be-located-at-91 :stable :time (n2 / now)