[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/nafise-sadat-moosavi/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Nafise Sadat Moosavi # 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](https://md.mova.elamur.ai/free/en/docs/papers/topics/coreference-resolution/); often with [Michael Strube](https://md.mova.elamur.ai/free/en/docs/papers/authors/michael-strube/), [Massimo Poesio](https://md.mova.elamur.ai/free/en/docs/papers/authors/massimo-poesio/), [Juntao Yu](https://md.mova.elamur.ai/free/en/docs/papers/authors/juntao-yu/). [OpenAlex](https://openalex.org/A5054918343) · [ORCID](https://orcid.org/0000-0002-8332-307X) · [**h-index 12**](https://openalex.org/authors/A5054918343) · [717 citations](https://openalex.org/authors/A5054918343) · [92 works](https://openalex.org/works?filter=author.id:A5054918343) — 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](https://scholar.google.com/citations?view_op=search_authors&mauthors=Nafise+Sadat+Moosavi) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Nafise+Sadat+Moosavi) · [dblp](https://dblp.org/search?q=Nafise+Sadat+Moosavi) · [ACL Anthology](https://aclanthology.org/search/?q=Nafise+Sadat+Moosavi) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Nafise+Sadat+Moosavi) Topics: [Coreference resolution](https://md.mova.elamur.ai/free/en/docs/papers/topics/coreference-resolution/) 6 ## Papers 1. **[Scoring Coreference Chains with Split-Antecedent Anaphors](https://md.mova.elamur.ai/free/en/docs/papers/paun-2023-scoring-coreference-chains-split-antecedent/)** *(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. 2. **[Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution](https://md.mova.elamur.ai/free/en/docs/papers/yu-2020-free-plural-unrestricted-split-antecedent/)** *(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… 3. **[Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection](https://md.mova.elamur.ai/free/en/docs/papers/moosavi-2019-automatically-extracted-minimum-spans-disentangle/)** *(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. 4. **[Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers](https://md.mova.elamur.ai/free/en/docs/papers/moosavi-2018-linguistic-features-improve-generalization-capability/)** *(2018)* Neural coreference resolvers that win on CoNLL-2012 lose their ranking on WikiCoref, which uses the same guidelines. 5. **[Lexical Features in Coreference Resolution: To be Used With Caution](https://md.mova.elamur.ai/free/en/docs/papers/moosavi-2017-lexical-features-coreference-resolution-be/)** *(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). 6. **[Which Coreference Evaluation Metric Do You Trust? A Proposal for a Link-based Entity Aware Metric](https://md.mova.elamur.ai/free/en/docs/papers/moosavi-2016-which-coreference-evaluation-metric-do/)** *(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) - [Michael Strube](https://md.mova.elamur.ai/free/en/docs/papers/authors/michael-strube/) ×4 - [Massimo Poesio](https://md.mova.elamur.ai/free/en/docs/papers/authors/massimo-poesio/) ×3 - [Juntao Yu](https://md.mova.elamur.ai/free/en/docs/papers/authors/juntao-yu/) ×2 - [Silviu Paun](https://md.mova.elamur.ai/free/en/docs/papers/authors/silviu-paun/) ×2 - [Leo Born](https://md.mova.elamur.ai/free/en/docs/papers/authors/leo-born/) - [← previous Nadir Durrani](https://md.mova.elamur.ai/free/en/docs/papers/authors/nadir-durrani/) - [next → Najoung Kim](https://md.mova.elamur.ai/free/en/docs/papers/authors/najoung-kim/) - [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)