Nafise Sadat Moosavi

6 paper cards in Mova's library · 2016–2023

Nafise Sadat Moosavi wrote 6 of the papers Mova reads, in 2016–2023, most of them on Coreference resolution; often with Michael Strube, Massimo Poesio, Juntao Yu.

OpenAlex · ORCID · h-index 12 · 717 citations · 92 works — openalex, 2026-10-18

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

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Coreference resolution 6

Papers

Scoring Coreference Chains with Split-Antecedent Anaphors (2023)
Standard coreference scorers (MUC, B3, CEAF, LEA, BLANC) assume that every anaphor refers to one entity, so they cannot score split-antecedent references such as "they" for "John" and "Mary" in "John met Mary.
Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution (2020)
Most coreference systems give a mention one antecedent, so «John met Mary. They had a chat» cannot be resolved: they refers to two separately introduced entities. The paper builds the first model for this split-antecedent case in general, on ARRAU (news, dialogue, fiction, medical; 507 training anaphors), with gold…
Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection (2019)
Scoring coreference by maximum spans mixes coreference errors with boundary errors such as PP attachment: «an extensive presence» and «an extensive presence, of course in this country» count as different mentions, and the system is penalised as if it had linked the wrong thing.
Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers (2018)
Neural coreference resolvers that win on CoNLL-2012 lose their ranking on WikiCoref, which uses the same guidelines.
Lexical Features in Coreference Resolution: To be Used With Caution (2017)
Learned coreference resolvers owe much of their gain over rule systems to lexical features (surface words or embeddings of heads, first/last words, context).
Which Coreference Evaluation Metric Do You Trust? A Proposal for a Link-based Entity Aware Metric (2016)
The paper shows a flaw shared by B³, CEAF and BLANC, the «mention identification effect»: because they count common mentions rather than links, a system gains recall and precision merely by putting gold mentions into its output, even when those mentions are linked wrongly; experiments on CoNLL outputs that add…

Co-authors (5)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/nafise-sadat-moosavi/