2026-09-19T02:21:52.394958800Zhttps://opus.uleth.ca/server/oai/request
oai:opus.uleth.ca:10133/70662025-07-16T05:04:36Zcom_10133_3346com_10133_1com_10133_296col_10133_3347col_10133_298
ULethbridge OPUS Repository supervisor Chali, Yllias author Mahamud, Al Hasib author University of Lethbridge. Faculty of Arts and Science 2025-07-15T19:28:03Z 2025-07-15T19:28:03Z 2025 https://hdl.handle.net/10133/7066 Question generation is a task of Natural Language Processing where the goal is to generate fluent, grammatically correct, and error-free questions based on a given input context and optionally an answer. Multi-hop question generation is a more complex task compared to traditional single-hop question generation, as it requires reasoning over multiple information from multiple input contexts in generating multi-hop questions. In our work, we have addressed the challenge of building a multi-hop question generation system by combining the knowledge graphs with Large Language Models (LLMs). We have designed a framework KG4QG(Knowledge Graph for Question Generation), where knowledge graphs are generated from the input contexts. For the knowledge graph embedding, we use a Graph Attention Network, and for input texts embedding, we leverage a Sentence Transformer. Finally, we apply the BART and T5 models as Large Language Models to generate multi-hop questions from our proposed model. Using the HotpotQA dataset to evaluate the performance of our KG4QG framework, our proposed methodology shows enhanced performance over the previous methodologies en Question generation Large Language Models Graph Attention Network Multi-hop question Knowledge graph KG4QG: combining knowledge graph with large language models for multi-hop question generation Thesis PGI+VGhlIEdvdmVybm9ycyBvZiB0aGUgVW5pdmVyc2l0eSBvZiBMZXRoYnJpZGdlICjigJxVbml2ZXJzaXR5IG9mIExldGhicmlkZ2XigJ0pIHwgTm9uLUV4Y2x1c2l2ZSBUaGVzaXMgTGljZW5zZSBBZ3JlZW1lbnQ8L2I+CjxwPkluIGNvbnNpZGVyYXRpb24gb2YgdGhlIFVuaXZlcnNpdHkgb2YgTGV0aGJyaWRnZSBhZ3JlZWluZyB0byBtYWtlIHlvdXIgdGhlc2lzL2Rpc3NlcnRhdGlvbiAodGhlICJUaGVzaXMiKSBhdmFpbGFibGUgdG8gaW50ZXJlc3RlZCBwZXJzb25zLCB5b3UgYWdyZWUgYXMgZm9sbG93czogPC9wPgo8b2w+CjxsaT5Zb3UgaGVyZWJ5IGdyYW50IHRvIHRoZSBVbml2ZXJzaXR5IG9mIExldGhicmlkZ2UgYSBub24tZXhjbHVzaXZlLCB3b3JsZHdpZGUsIGlycmV2b2NhYmxlLCByb3lhbHR5LWZyZWUgbGljZW5zZSB0byBhcmNoaXZlLCBwcmVzZXJ2ZSwgcHJvZHVjZSwgcmVwcm9kdWNlLCBwdWJsaXNoLCBjb21tdW5pY2F0ZSwgY29udmVydCBpbnRvIGFueSBmb3JtYXQsIGNvbW11bmljYXRlIGFuZCBkaXN0cmlidXRlIHRoZSBUaGVzaXMsIGluY2x1ZGluZyB0aGUgVGhlc2lzIGFic3RyYWN0LCBpbiBhbnkgZm9ybWF0IGFuZCBpbiBhbnkgbWVkaXVtIGZvciBub24tY29tbWVyY2lhbCBwdXJwb3NlcyBmb3IgdGhlIGZ1bGwgdGVybSBvZiB0aGUgY29weXJpZ2h0LCBpbmNsdWRpbmcgYnV0IG5vdCBsaW1pdGVkIHRvIHRoZSByaWdodCB0bzoKPG9sIHR5cGU9ImEiPjxsaT5tYWtlIHRoZSBUaGVzaXMgYXZhaWxhYmxlIGluIHByaW50IG9yIG9ubGluZSBieSB0ZWxlY29tbXVuaWNhdGlvbiB0byB0aGUgcHVibGljLCBpbmNsdWRpbmcgdmlhIHRoZSBpbnRlcm5ldCBhbmQgZmFjc2ltaWxlIHRyYW5zbWlzc2lvbiwgZm9yIG5vbi1jb21tZXJjaWFsIHB1cnBvc2VzOzwvbGk+CjxsaT5kaXN0cmlidXRlIHRoZSBUaGVzaXMgdGhyb3VnaCB0aGUgbGlicmFyeSwgaW50ZXJsaWJyYXJ5IGFuZCBwdWJsaWMgbG9hbjs8L2xpPgo8bGk+ZGlnaXRpemUsIHBob3RvY29weSBhbmQgbWljcm9maWNoZSB0aGUgVGhlc2lzOzwvbGk+CjxsaT5zdWItbGljZW5jZSB0byBMaWJyYXJ5IGFuZCBBcmNoaXZlcyBDYW5hZGEgYW55IG9mIHRoZSBhY3Rpb25zIG1lbnRpb25lZCBhYm92ZTsgYW5kIDwvbGk+CjxsaT5zdWItbGljZW5jZSB0byBQcm9RdWVzdCBEaXNzZXJ0YXRpb25zIGFuZCBUaGVzZXMgR2xvYmFsIGFueSBvZiB0aGUgYWN0aW9ucyBtZW50aW9uZWQgYWJvdmUuICA8L2xpPjwvPC9vbD48L2xpPgo8bGk+WW91IGNvbmZpcm0gdGhlIGZvbGxvd2luZyBzdGF0ZW1lbnRzIHRvIGJlIHRydWUgYW5kIGFjY3VyYXRlOgo8b2wgdHlwZT0iYSI+PGxpPnlvdSBoYXZlIHRoZSByaWdodCBhbmQgYXV0aG9yaXR5IHRvIGdyYW50IHRoZSByaWdodHMgc2V0IG91dCBpbiB0aGlzIGxpY2Vuc2U7IDwvbGk+CjxsaT50aGUgVGhlc2lzIGlzIHlvdXIgb3JpZ2luYWwgd29yayBhbmQgaXMgYW4gdW4tYW1lbmRlZCBjb3B5IG9mIHRoZSBmaW5hbCB2ZXJzaW9uIGFwcHJvdmVkIGJ5IHRoZSBEZWFuIG9mIHRoZSBTY2hvb2wgb2YgR3JhZHVhdGUgU3R1ZGllczsgPC9saT4KPGxpPnRoZSBUaGVzaXMgZG9lcyBub3QgaW5mcmluZ2UgdGhlIGNvcHlyaWdodCBvciBpbnRlbGxlY3R1YWwgcHJvcGVydHkgcmlnaHRzIG9mIGFueSBvdGhlciBwZXJzb247IDwvbGk+CjxsaT5pZiB0aGUgVGhlc2lzIGNvbnRhaW5zIG1hdGVyaWFsIGZvciB3aGljaCwgdW5kZXIgdGhlIHRlcm1zIG9mIHRoZSBDb3B5cmlnaHQgQWN0LCB3cml0dGVuIHBlcm1pc3Npb24gb2YgdGhlIGNvcHlyaWdodCBvd25lcihzKSBpcyByZXF1aXJlZCB0byBpbmNsdWRlIHRoZSB3b3JrIChvciBwYXJ0IHRoZXJlb2YsIGFzIHRoZSBjYXNlIG1heSBiZSkgaW4gdGhlIFRoZXNpcywgdGhlbiBib3RoIG9mIHRoZSBmb2xsb3dpbmcgYXBwbHk6CjxvbCB0eXBlPSJpIj48bGk+dGhlIG1hdGVyaWFsIGhhcyBiZWVuIGNsZWFybHkgYW5kIGFwcHJvcHJpYXRlbHkgaWRlbnRpZmllZCBhbmQgYWNrbm93bGVkZ2VkOyBhbmQgPC9saT4KPGxpPnlvdSBoYXZlIG9idGFpbmVkIHdyaXR0ZW4gcGVybWlzc2lvbiBvZiB0aGUgY29weXJpZ2h0IG93bmVyKHMpLCBmb3IgdGhlIGZ1bGwgdGVybSBvZiBjb3B5cmlnaHQgcHJvdGVjdGlvbiwgdG8gaW5jbHVkZSB0aGUgd29yayAob3IgcGFydCB0aGVyZW9mLCBhcyB0aGUgY2FzZSBtYXkgYmUpIGluIHRoZSBUaGVzaXMgYW5kIHRvIGdyYW50IHRvIHRoZSBVbml2ZXJzaXR5IG9mIExldGhicmlkZ2UgdGhlIHJpZ2h0cyBzZXQgb3V0IGluIHRoaXMgbGljZW5zZTsgPC9saT48L29sPiA8L2xpPgo8bGk+IHRoZSBUaGVzaXMgZG9lcyBub3QgY29udGFpbiBhbnkgY29uZmlkZW50aWFsIG9yIHByb3ByaWV0YXJ5IGluZm9ybWF0aW9uIGJlbG9uZ2luZyB0byBvdGhlcnMsIG90aGVyIHRoYW4gaW5mb3JtYXRpb24gaW5jbHVkZWQgdW5kZXIgU2VjdGlvbiAyIGQpIGFib3ZlOyA8L2xpPgo8bGk+dGhlIFRoZXNpcyBkb2VzIG5vdCBjb250YWluIGFueSBsaWJlbG91cyBvciBvdGhlciB1bmxhd2Z1bCBtYXR0ZXIgYW5kIGRvZXMgbm90IGludmFkZSB0aGUgcHJpdmFjeSBvZiBhbnkgcGVyc29uczsgYW5kIDwvbGk+CjxsaT50aGVyZSBhcmUgbm8gdW5leHBpcmVkIHB1YmxpY2F0aW9uIGRlbGF5cyBvbiB0aGUgZGlzdHJpYnV0aW9uIG9mIHRoZSBUaGVzaXMuIDwvbGk+PC9vbD4gPC9saT4KPGxpPllvdSBhcmUgYXdhcmUgdGhhdCB5b3UgcmV0YWluIHlvdXIgY29weXJpZ2h0IG93bmVyc2hpcCBhbmQgbW9yYWwgcmlnaHRzIGluIHRoZSBUaGVzaXMgYW5kIG1heSBkZWFsIHdpdGggdGhlIFRoZXNpcyBpbiBhbnkgd2F5IGNvbnNpc3RlbnQgd2l0aCB0aGUgcmlnaHRzIGdyYW50ZWQgdG8gdGhlIFVuaXZlcnNpdHkgb2YgTGV0aGJyaWRnZSBpbiB0aGlzIGxpY2Vuc2UuIFlvdSB1bmRlcnRha2UgdG8gc3VibWl0IHlvdXIgVGhlc2lzLCBpbmNsdWRpbmcgdGhlIFRoZXNpcyBhYnN0cmFjdCwgdGhyb3VnaCB0aGUgVW5pdmVyc2l0eSBvZiBMZXRoYnJpZGdlIHRvIExpYnJhcnkgYW5kIEFyY2hpdmVzIENhbmFkYS4gWW91IHByb21pc2UgdG8gaW5mb3JtIGFueSBwZXJzb24gdG8gd2hvbSB5b3UgbWF5IGhlcmVhZnRlciBhc3NpZ24gb3IgbGljZW5zZSB5b3VyIGNvcHlyaWdodCBpbiB5b3VyIFRoZXNpcyBvZiB0aGUgcmlnaHRzIGdyYW50ZWQgdG8gdGhlIFVuaXZlcnNpdHkgb2YgTGV0aGJyaWRnZSBpbiB0aGlzIGxpY2Vuc2UuIFlvdSBhZ3JlZSB0aGF0IHRoZSBVbml2ZXJzaXR5IG9mIExldGhicmlkZ2UgaXMgbm90IHJlc3BvbnNpYmxlIGZvciBhbnkgbWlzdXNlIG9mIHRoZSBUaGVzaXMgYnkgdGhpcmQgcGFydGllcyB3aG8gYWNjZXNzIHRoZSBUaGVzaXMgdGhyb3VnaCB0aGUgVW5pdmVyc2l0eSBvZiBMZXRoYnJpZGdl4oCZcyBmYWNpbGl0aWVzLjwvbGk+PC9vbD4= URL http://localhost:4000/bitstreams/c3e63347-7d3d-4f5c-a1b9-617da883ffab/download File MD5 76dc736e6064a9fb504eea443f18554c 786808 application/pdf MAHAMUD_AL HASIB_MSC_2025.pdf URL http://localhost:4000/bitstreams/deb75d13-09dc-4b54-b9bb-f8b50c14eb79/download File MD5 01bfd57c4c93f17383c5bb6a50006a7e 100355 text/plain MAHAMUD_AL HASIB_MSC_2025.pdf.txt