CorPipe 24

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10493028" target="_blank" >RIV/00216208:11320/24:10493028 - isvavai.cz</a>

Result on the web

<a href="https://github.com/ufal/crac2024-corpipe" target="_blank" >https://github.com/ufal/crac2024-corpipe</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

CorPipe 24

Original language description

We present CorPipe 24, the winning entry to the CRAC 2024 Shared Task on Multilingual Coreference Resolution. In this third iteration of the shared task, a novel objective is to also predict empty nodes needed for zero coreference mentions (while the empty nodes were given on input in previous years). This way, coreference resolution can be performed on raw text. We evaluate two model variants: a two-stage approach (where the empty nodes are predicted first using a pretrained encoder model and then processed together with sentence words by another pretrained model) and a single-stage approach (where a single pretrained encoder model generates empty nodes, coreference mentions, and coreference links jointly). In both settings, CorPipe surpasses other participants by a large margin of 3.9 and 2.8 percent points, respectively. The source code and the trained model are available at https://github.com/ufal/crac2024-corpipe.

Czech name

—

Czech description

—

Type

R - Software

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GX20-16819X" target="_blank" >GX20-16819X: Language Understanding: from Syntax to Discourse</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Internal product ID

[https://github.com/ufal/crac202

Technical parameters

Výsledek volně dostupný na adrese https://github.com/ufal/crac2024-corpipe.

Economical parameters

146419

Owner IČO

00216208

Owner name

Univerzita Karlova