Massimo Poesio

Ideas Mova took (1)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

• measured, no gain — Implement the discourse-deixis baseline as a sieve in coref/src/sieve.rs (the disabled demonstratives slot is the place): this/that (and it as subject of happened, was true, means) not followed by a noun → the preceding clause, as an event mention with a… (The CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and… · deixis sieve (event «it», bare this/that → previous clause, as an added clause mention): 17 of 141 right on GUM dev, −0.76/−0.09 CoNLL gold; in coref, off by…)

Papers

1. 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.
2. The CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue (2022)
   The second edition of a shared task on anaphora in dialogue, with three tasks: identity anaphora (including split antecedents and singletons), bridging reference, and discourse deixis (a pronoun such as that or this referring to an event, fact or utterance).
3. The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue (2021)
   The shared task asks systems to find anaphoric relations in conversation, a genre that OntoNotes-style corpora barely cover.
4. 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…
5. 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.
6. ARRAU: Linguistically-Motivated Annotation of Anaphoric Descriptions (2016)
   The paper presents the second release of ARRAU, a multi-domain corpus for anaphora. Its domains are news (from the RST Discourse Treebank), task-oriented dialogue (TRAINS), fiction (PEAR) and medical leaflets (GNOME). Release 2 has 552 documents, 348,072 tokens and 99,582 markables. Release 1 had 264 documents…
7. Merging PropBank, NomBank, TimeBank, Penn Discourse Treebank and Coreference (2005)
   Separate annotation projects each cover one part of semantics: PropBank and NomBank (predicate-argument structure of verbs and nouns), TimeBank (events, times and their links), the Penn Discourse Treebank (connectives as predicates), and Essex coreference (MATE scheme).
8. Identifying Broken Plurals in Unvowelised Arabic Text (2004)
   Broken plurals (formed by changing the consonant pattern of the singular, not by adding a suffix) cannot be undone by affix stripping, so a light stemmer leaves them as separate stems.

Co-authors (21)

• Juntao Yu ×4
• Michael Strube ×3
• Nafise Sadat Moosavi ×3
• Carolyn Rosé ×2
• Ramesh Manuvinakurike ×2
• Silviu Paun ×2
• Sopan Khosla ×2
• Vincent Ng ×2
• Abduelbaset Goweder
• Adam Meyers
• Anne De Roeck
• Antonella Bristot
• Federica Cavicchio
• James Pustejovsky
• Jeff Reynolds
• Kepa Rodriguez
• Leo Born
• Lori Levin
• Martha Palmer
• Olga Uryupina
• Ron Artstein

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/massimo-poesio/