Chop and change: Anaphora resolution in instructional cooking videos - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Chop and change: Anaphora resolution in instructional cooking videos

Abstract

Linguistic ambiguities arising from changes in entities in action flows are a key challenge in instructional cooking videos. In particular, temporally evolving entities present rich and to date understudied challenges for anaphora resolution. For example "oil" mixed with "salt" is later referred to as a "mixture". In this paper we propose novel annotation guidelines to annotate recipes for the anaphora resolution task, reflecting change in entities. Moreover, we present experimental results for end-to-end multimodal anaphora resolution with the new annotation scheme and propose the use of temporal features for performance improvement.
Fichier principal
Vignette du fichier
oguz_AACL22.pdf (2.88 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03807530 , version 1 (10-10-2022)

Identifiers

  • HAL Id : hal-03807530 , version 1

Cite

Cennet Oguz, Ivana Kruijff-Korbayová, Pascal Denis, Emmanuel Vincent, Josef van Genabith. Chop and change: Anaphora resolution in instructional cooking videos. Findings of AACL-IJCNLP 2022 - 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics - 12th International Joint Conference on Natural Language Processing, Nov 2022, Taipeh, Taiwan. ⟨hal-03807530⟩
84 View
151 Download

Share

Gmail Facebook X LinkedIn More