Mark Yatskar

2 paper cards in Mova's library · 2017–2023

Mark Yatskar wrote 2 of the papers Mova reads, in 2017–2023, most of them on Coreference resolution, Machine translation; often with Chaitanya Malaviya, Ioannis Konstas, Luke Zettlemoyer.

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

Papers

AmbiCoref: Evaluating Human and Model Sensitivity to Ambiguous Coreference (2023)
The paper asks whether coreference models react to pronoun ambiguity as people do. It builds AmbiCoref, a corpus of minimal sentence pairs: an ambiguous and an unambiguous sentence differ only in one verb phrase (for example "Abby told Brittney that she upset Courtney" against "hugged"). The templates come from four…
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation (2017)
The paper applies sequence-to-sequence neural models to both AMR parsing and AMR generation. The main obstacle is data sparsity, so the authors pretrain on millions of unlabelled Gigaword sentences: a parser labels them, a generator is pretrained on those pairs, and then both are fine-tuned on the 16,833 gold pairs.…