Aram Galstyan

2 paper cards in Mova's library · 2022–2023

Aram Galstyan wrote 2 of the papers Mova reads, in 2022–2023, most of them on Machine translation; often with Anoop Kumar, Kai-Wei Chang, Kuan-Hao Huang.

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

Papers

ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation (2023)
ParaAMR builds about 15 million paraphrase pairs by AMR back-translation. Each source sentence is parsed to an AMR graph; a different node is chosen as the focus (the main assertion); the modified graph is linearised and a sentence is generated from it. Candidates with high perplexity under a language model are…
Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations (2022)
AMRPG generates a paraphrase that follows a requested syntactic form without any paraphrase pairs. It encodes the input twice: an AMR graph gives a semantic embedding, and the constituency parse gives a syntactic embedding. A decoder learns to reconstruct the input from the two. At test time the syntactic embedding…