The definition of words is the fundamental and crucial linguistic concept. Any changes in word definition lead to changes in the theoretical system of the respective language. Traditionally, researchers in Natural Language Processing (NLP) for Vietnamese texts believe Vietnamese words are constructed from syllables. However, their works did not explicitly mention which linguistic theory they followed for this assumption. Although there are no theoretical guarantees, most NLP studies in Vietnamese accept this assumption. Consequently, word segmentation is recognized as one of the essential stages in NLP for Vietnamese texts. In this study, we address the role of word segmentation for Vietnamese texts from linguistic perspectives. Through our extensive experiments, we show that, based on linguistic theories, performing word segmentation is not appropriate for Vietnamese text understanding. Moreover, we present a novel method, Vietnamese Word TransFormer (ViWordFormer), for modeling Vietnamese word formation. Experimental results indicate that our method is appropriate for modeling Vietnamese word formation from both theoretical and experimental aspects and embark on a novel approach to Vietnamese word representation.

The Data Science and Advanced Analytics (DSAA) 2023 competition [1] focuses on proposing link prediction methods to solve challenges about network-like data structure, such as network reconstruction, network development, etc., from articles on Wikipedia. In this challenge, our “UIT Dark Cow” team proposes the Mutual Attention Transformer (MAT) method to predict if there is a link between two Wikipedia pages. Our method achieved the 5th and 4th position on the leaderboard for the public and private tests, respectively. Our source code is publicly available for the ease of experimental re-implementation at the following link: https://github.com/minhquan6203/source-code-dsaa-2023.