Conference Paper Published

Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets

Pranav, A, Cong, Y., Chersoni, E., Hsu, Y. Y., & Lenci, A. (2024). Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 3610-3627.

URL: https://aclanthology.org/2024.lrec-main.320

Abstract

The field of Distributional Semantics has recently undergone important changes, with the contextual representations produced by Transformers taking the place of static word embeddings models. Noticeably, previous studies comparing the two types of vectors have only focused on the English language and a limited number of models. In our study, we present a comparative evaluation of static and contextualized distributional models for Mandarin Chinese, focusing on a range of intrinsic tasks. Our results reveal that static models remain stronger for some of the classical tasks that consider word meaning independent of context, while contextualized models excel in identifying semantic relations between word pairs and in the categorization of words into abstract semantic classes. The code and datasets are available at https://github.com/pranav-ust/chinese-dsm.

Keywords

Distributional Semantic Models, Mandarin Chinese, Semantic Similarity, Transformers