Payal Khullar

4 paper cards in Mova's library · 2019–2021

Payal Khullar wrote 4 of the papers Mova reads, in 2019–2021, most of them on Coreference resolution, Treebanks, Machine translation; often with Manish Shrivastava, Allen Antony, Arghya Bhattacharya.

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

Papers

Are Ellipses Important for Machine Translation? (2021)
The paper tests how much ellipsis hurts neural machine translation, from English into Hindi and Telugu. It uses 1,500 sentences: 500 each of nominal, verbal and clausal ellipsis, taken from the Bos and Spenader VPE corpus, a curated ellipsis set and other annotated corpora. Each sentence is also given in a version…
Finding The Right One and Resolving it (2020)
One-anaphora is the use of the word "one" or "ones" for a noun head, as in "the black one". The paper separates it from the determinative use of "one" as a numeral, a confusion that has weakened earlier computational work. The authors annotate one-anaphora with their antecedents in the British National Corpus and…
NoEl: An Annotated Corpus for Noun Ellipsis in English (2020)
The authors annotate the first 100 movies of the Cornell Movie Dialogs corpus, about 672,000 tokens, for noun ellipsis: a licensor (a cardinal, ordinal, possessive, determiner, quantifier or adjective) whose head noun is left out.
Using Syntax to Resolve NPE in English (2019)
The paper describes a rule-based system for noun phrase ellipsis (NPE), where the head noun is omitted, as in "We are all partying at Mary's [e]".