Anette Frank

4 paper cards in Mova's library · 1998–2021

Anette Frank wrote 4 of the papers Mova reads, in 1998–2021, most of them on Machine translation, Coreference resolution; often with Juri Opitz, Ana Marasović, Angel Daza.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR (2021)
The paper proposes MF-beta, a metric for AMR-to-text output with two parts combined in an F-beta style. The meaning part (M) parses the generated sentence back to an AMR with a strong parser and scores the graph overlap with the input AMR, using a graded Smatch that gives partial credit for near-matching concepts.…
Weisfeiler-Leman in the Bamboo: Novel AMR Graph Metrics and a Benchmark for AMR Graph Similarity (2021)
AMR similarity metrics (Smatch, S2match, SemBLEU and others) had never been compared on one benchmark against human ratings.
A Mention-Ranking Model for Abstract Anaphora Resolution (2017)
Abstract anaphors (this trend, this, that, it referring to a proposition, fact or event) have almost no annotated training data.
Syntactic and Semantic Transfer with F-Structures (1998)
The paper gives two ways to transfer between languages from LFG f-structures, the attribute-value syntax of LFG.