Constructing Uyghur Commonsense Knowledge Base by Knowledge Projection

Abstract

Although considerable effort has been devoted to building commonsense knowledge bases (CKB), it is still not available for many low-resource languages such as Uyghur because of expensive construction cost. Focusing on this issue, we proposed a cross-lingual knowledge-projection method to construct an Uyghur CKB by projecting ConceptNet’s Chinese facts into Uyghur. We used a Chinese–Uyghur bilingual dictionary to get high-quality entity translation in facts and employed a back-translation method to eliminate the entity-translation ambiguity. Moreover, to tackle the inner relation ambiguity in translated facts, we made a hand-crafted rule to convert the structured facts into natural-language phrases and built the Chinese–Uyghur lingual phrases based on the similarity of phrases that corresponded to the bilingual semantic similarity scoring model. Experimental results show that the accuracy of our semantic similarity scoring model reached 94.75% for our task, and they successfully project 55,872 Chinese facts into Uyghur as well as obtain 67,375 Uyghur facts within a very short period.

Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning

“…Several studies to reduce the number of differences in knowledge base between resource-rich languages and lowresource languages have been conducted (Feng et al 2016;Otani et al 2018;Anwar et al 2019;Moussallem, Soru, and Ngomo 2019). To expand upon low-resource knowledge, the authors proposed a machine translation (MT) based approach, a method for finding the triple with the highest validity score among translated candidates from one source triple.…”

“…Several studies have proposed scoring methods to measure the validity of the translated triples to resolve the ambiguity problem (Feng et al 2016;Otani et al 2018;Anwar et al 2019;Moussallem, Soru, and Ngomo 2019). The most common constraint in those studies is that the proposed methods require manually labeled data or handcrafted templates.…”