Patrick Xia

2 paper cards in Mova's library · 2020–2021

Patrick Xia wrote 2 of the papers Mova reads, in 2020–2021, most of them on Coreference resolution; often with Benjamin Van Durme, João Sedoc, Karen Livescu.

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

Papers

On Generalization in Coreference Resolution (2021)
The paper asks whether coreference models trained on one dataset transfer to others. It consolidates eight datasets (OntoNotes, LitBank, PreCo as training sets; Character Identification, WikiCoref, Quiz Bowl, GAP and Winograd-style WSC as evaluation or analysis sets) and trains a long-document entity-ranking model…
Incremental Neural Coreference Resolution in Constant Memory (2020)
The paper turns a strong all-pairs coreference model (SpanBERT, Joshi et al. 2020) into an incremental one that reads a document segment by segment and keeps a fixed-size list of entities. Each new mention is scored against entity representations (not individual earlier mentions); it joins the best entity if the…