Topicalization in Language Models: A Case Study on Japanese

Riki Fujihara, Tatsuki Kuribayashi, Kaori Abe, Ryoko Tokuhisa, Kentaro Inui


Abstract
Humans use different wordings depending on the context to facilitate efficient communication. For example, instead of completely new information, information related to the preceding context is typically placed at the sentence-initial position. In this study, we analyze whether neural language models (LMs) can capture such discourse-level preferences in text generation. Specifically, we focus on a particular aspect of discourse, namely the topic-comment structure. To analyze the linguistic knowledge of LMs separately, we chose the Japanese language, a topic-prominent language, for designing probing tasks, and we created human topicalization judgment data by crowdsourcing. Our experimental results suggest that LMs have different generalizations from humans; LMs exhibited less context-dependent behaviors toward topicalization judgment. These results highlight the need for the additional inductive biases to guide LMs to achieve successful discourse-level generalization.
Anthology ID:
2022.coling-1.71
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
851–862
Language:
URL:
https://aclanthology.org/2022.coling-1.71
DOI:
Bibkey:
Cite (ACL):
Riki Fujihara, Tatsuki Kuribayashi, Kaori Abe, Ryoko Tokuhisa, and Kentaro Inui. 2022. Topicalization in Language Models: A Case Study on Japanese. In Proceedings of the 29th International Conference on Computational Linguistics, pages 851–862, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Topicalization in Language Models: A Case Study on Japanese (Fujihara et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.71.pdf