Cloze Evaluation for Deeper Understanding of Commonsense Stories in Indonesian

Document Type

Conference Proceeding

Publication Title

CSRR 2022 - 1st Workshop on Commonsense Representation and Reasoning

Abstract

Story comprehension that involves complex causal and temporal relations is a critical task in NLP, but previous studies have focused predominantly on English, leaving open the question of how the findings generalize to other languages, such as Indonesian. In this paper, we follow the Story Cloze Test framework of Mostafazadeh et al. (2016) in evaluating story understanding in Indonesian, by constructing a four-sentence story with one correct ending and one incorrect ending. To investigate commonsense knowledge acquisition in language models, we experimented with: (1) a classification task to predict the correct ending; and (2) a generation task to complete the story with a single sentence. We investigate these tasks in two settings: (i) monolingual training and (ii) zero-shot cross-lingual transfer between Indonesian and English. © 2022 Association for Computational Linguistics.

First Page

8

Last Page

16

DOI

10.18653/v1/2022.csrr-1.2

Publication Date

5-2022

Keywords

Classification (of information), Computational linguistics, Natural language processing systems

Comments

IR Deposit conditions: non-described

Share

COinS