We present the first comprehensive set of guidelines for German Abstract Meaning Representation (Deutsche AMR, DeAMR) along with an annotated corpus of 400 DeAMR. Taking English AMR (EnAMR) as our starting point, we propose significant adaptations to faithfully represent the structure and semantics of German, focusing particularly on verb frames, compound words, and modality. We validate our annotation through inter-annotator agreement and further evaluate our corpus with a comparison of structural divergences between EnAMR and DeAMR on parallel sentences, replicating previous work that finds both cases of cross-lingual structural alignment and cases of meaningful linguistic divergence. Finally, we fine-tune state-of-the-art multi-lingual and cross-lingual AMR parsers on our corpus and find that, while our small corpus is insufficient to produce quality output, there is a need to continue develop and evaluate against gold non-English AMR data.

This paper evaluates how well English Abstract Meaning Representation parsers process an important and frequent kind of Long-Distance Dependency construction, namely, relative clauses (RCs). On two syntactically parsed datasets, we evaluate five AMR parsers at recovering the semantic reentrancies triggered by different syntactic subtypes of relative clauses. Our findings reveal a general difficulty among parsers at predicting such reentrancies, with recall below 64% on the EWT corpus. The sequence-to-sequence models (regardless of whether structural biases were included in training) outperform the compositional model. An analysis by relative clause subtype shows that passive subject RCs are the easiest, and oblique and reduced RCs the most challenging, for AMR parsers.

This work studies the plausibility of sequence-to-sequence neural networks as models of morphological acquisition by humans. We replicate the findings of Kirov and Cotterell (2018) on the well-known challenge of the English past tense and examine their generalizability to two related but morphologically richer languages, namely Dutch and German. Using a new dataset of English/Dutch/German (ir)regular verb forms, we show that the major findings of Kirov and Cotterell (2018) hold for all three languages, including the observation of over-regularization errors and micro U-shape learning trajectories. At the same time, we observe troublesome cases of non human-like errors similar to those reported by recent follow-up studies with different languages or neural architectures. Finally, we study the possibility of switching to orthographic input in the absence of pronunciation information and show this can have a non-negligible impact on the simulation results, with possibly misleading findings.