This paper explores the integration of graph knowledge from linguistic
ontologies into multilingual Large Language Models (LLMs) using adapters to
improve performance for low-resource languages (LRLs) in sentiment analysis
(SA) and named entity recognition (NER). Building upon successful
parameter-efficient fine-tuning techniques, such as K-ADAPTER and MAD-X, we
propose a similar approach for incorporating knowledge from multilingual
graphs, connecting concepts in various languages with each other through
linguistic relationships, into multilingual LLMs for LRLs. Specifically, we
focus on eight LRLs -- Maltese, Bulgarian, Indonesian, Nepali, Javanese,
Uyghur, Tibetan, and Sinhala -- and employ language-specific adapters
fine-tuned on data extracted from the language-specific section of ConceptNet,
aiming to enable knowledge transfer across the languages covered by the
knowledge graph. We compare various fine-tuning objectives, including standard
Masked Language Modeling (MLM), MLM with full-word masking, and MLM with
targeted masking, to analyse their effectiveness in learning and integrating
the extracted graph data. Through empirical evaluation on language-specific
tasks, we assess how structured graph knowledge affects the performance of
multilingual LLMs for LRLs in SA and NER, providing insights into the potential
benefits of adapting language models for low-resource scenarios.

该研究探讨了将语义本体中的图谱知识整合到多语言大型语言模型中，通过适配器提高低资源语言在情感分析和命名实体识别中的性能，对八种低资源语言进行了实证评估，提供了适应低资源情景的语言模型优势的见解。

通过适配器在知识图谱上将多语言 LLMs 调整为资源不足的语言

Adapting Multilingual LLMs to Low-Resource Languages with Knowledge  Graphs via Adapters

The purpose of this work is to find out how different library classification
systems and linguistic ontologies arrange a particular domain of interest and
what are the limitations for information retrieval. We use knowledge
representation techniques and languages for construction of a domain specific
ontology. This ontology would help not only in problem solving, but it would
demonstrate the ease with which complex queries can be handled using principles
of domain ontology, thereby facilitating better information retrieval.

本文目的是研究不同的图书馆分类系统和语言本体论如何组织一个特定领域的信息，以及信息检索的限制，通过构建一个特定领域本体论来解决问题并展示使用相关本体论的原理处理复杂查询的便捷性，从而促进更好的信息检索。

应用多面向本体学原理重组教育机构域

Reorganizing Educational Institutional Domain using Faceted Ontological  Principles

The opacity of deep neural networks remains a challenge in deploying
solutions where explanation is as important as precision. We present ConceptX,
a human-in-the-loop framework for interpreting and annotating latent
representational space in pre-trained Language Models (pLMs). We use an
unsupervised method to discover concepts learned in these models and enable a
graphical interface for humans to generate explanations for the concepts. To
facilitate the process, we provide auto-annotations of the concepts (based on
traditional linguistic ontologies). Such annotations enable development of a
linguistic resource that directly represents latent concepts learned within
deep NLP models. These include not just traditional linguistic concepts, but
also task-specific or sensitive concepts (words grouped based on gender or
religious connotation) that helps the annotators to mark bias in the model. The
framework consists of two parts (i) concept discovery and (ii) annotation
platform.

该研究提出了 ConceptX 人在循环框架，用于解释深度语言模型中预训练隐藏表达空间，并提供自动生成的基于语言本体论的概念注释，以表示这些模型中学习到的隐含概念，从而帮助注释人员标记模型中的偏见。