BanglaAutoKG: Automatic Bangla Knowledge Graph Construction with Semantic Neural Graph Filtering

TL;DR

This paper introduces BanglaAutoKG, a novel framework that automatically constructs comprehensive Bangla Knowledge Graphs from any text using multilingual models, graph filtering, and GNN-based semantic filtering, addressing language resource scarcity.

Contribution

The paper presents the first automatic Bangla KG construction framework leveraging multilingual LLMs, graph filtering, and GNNs, filling a significant resource gap for Bengali language processing.

Findings

Effective automatic KG construction from Bangla text demonstrated.

Graph-based polynomial filters improve embedding alignment.

GNN-based semantic filtering enhances contextual accuracy.

Abstract

Knowledge Graphs (KGs) have proven essential in information processing and reasoning applications because they link related entities and give context-rich information, supporting efficient information retrieval and knowledge discovery; presenting information flow in a very effective manner. Despite being widely used globally, Bangla is relatively underrepresented in KGs due to a lack of comprehensive datasets, encoders, NER (named entity recognition) models, POS (part-of-speech) taggers, and lemmatizers, hindering efficient information processing and reasoning applications in the language. Addressing the KG scarcity in Bengali, we propose BanglaAutoKG, a pioneering framework that is able to automatically construct Bengali KGs from any Bangla text. We utilize multilingual LLMs to understand various languages and correlate entities and relations universally. By employing a translation dictionary to identify English equivalents and extracting word features from pre-trained BERT models, we construct the foundational KG. To reduce noise and align word embeddings with our goal, we employ graph-based polynomial filters. Lastly, we implement a GNN-based semantic filter, which elevates contextual understanding and trims unnecessary edges, culminating in the formation of the definitive KG. Empirical findings and case studies demonstrate the universal effectiveness of our model, capable of autonomously constructing semantically enriched KGs from any text.