The popularity of information technology has given rise to a growing interest in smart education and has provided the possibility of combining online and offline education. Knowledge graphs, an effective technology for knowledge representation and management, have been successfully utilized to manage massive educational resources. However, the existing research on constructing educational knowledge graphs ignores multiple modalities and their relationships, such as teacher speeches and their relationship with knowledge. To tackle this problem, we propose an automatic approach to construct multi-modal educational knowledge graphs that integrate speech as a modal resource to facilitate the reuse of educational resources. Specifically, we first propose a fine-tuned Bidirectional Encoder Representation from Transformers (BERT) model based on education lexicon, called EduBERT, which can adaptively capture effective information in the education field. We also add a Bidirectional Long Short-Term Memory-Conditional Random Field (BiLSTM-CRF) to effectively identify educational entities. Then, the locational information of the entity is incorporated into BERT to extract the educational relationship. In addition, to cover the shortage of traditional text-based knowledge graphs, we focus on collecting teacher speech to construct a multi-modal knowledge graph. We propose a speech-fusion method that links these data into the graph as a class of entities. The numeric results show that our proposed approach can manage and present various modes of educational resources and that it can provide better education services.

In today’s multilingual lexical databases, the majority of the world’s languages are under-represented. Beyond a mere issue of resource incompleteness, we show that existing lexical databases have structural limitations that result in a reduced expressivity on culturally-specific words and in mapping them across languages. In particular, the lexical meaning space of dominant languages, such as English, is represented more accurately while linguistically or culturally diverse languages are mapped in an approximate manner. Our paper assesses state-of-the-art multilingual lexical databases and evaluates their strengths and limitations with respect to their expressivity on lexical phenomena of linguistic diversity.

Lexical semantic changes spanning centuries can reveal the complicated developing process of language and social culture. In recent years, natural language processing (NLP) methods have been applied in this field to provide insight into the diachronic frequency change for word senses from large-scale historical corpus, for instance, analyzing which senses appear, increase, or decrease at which times. However, there is still a lack of Chinese diachronic corpus and dataset in this field to support supervised learning and text mining, and at the method level, few existing works analyze the Chinese semantic changes at the level of morpheme. This paper constructs a diachronic Chinese dataset for semantic tracking applications spanning 3000 years and extends the existing framework to the level of Chinese characters and morphemes, which contains four main steps of contextual sense representation, sense identification, morpheme sense mining, and diachronic semantic change representation. The experiment shows the effectiveness of our method in each step. Finally, in an interesting statistic, we discover the strong positive correlation of frequency and changing trend between monosyllabic word sense and the corresponding morpheme.

Yang Chi, Fausto Giunchiglia, Chuntao Li, Hao Xu. Findings of the Association for Computational Linguistics ACL 2024. 2024.