2026-09-19T02:42:38.682485400Zhttps://opus.uleth.ca/server/oai/request
oai:opus.uleth.ca:10133/63782022-11-08T07:05:09Zcom_10133_3346com_10133_1com_10133_296col_10133_3347col_10133_298
ULethbridge OPUS Repository supervisor Chali, Yllias author Emerson, John Robert author University of Lethbridge. Faculty of Arts and Science 2022-11-07T18:56:14Z 2022-11-07T18:56:14Z 2022 https://hdl.handle.net/10133/6378 Question generation is the parallel task of question answering, where given an input context and, optionally, an answer, the goal is to generate a relevant and fluent natural language question. Although recent works on question generation have experienced success by utilizing sequence-to-sequence models, there is a need for question generation models to handle increasingly complex input contexts to produce increasingly detailed questions. Multi-hop question generation is a more challenging task that aims to generate questions by connecting multiple facts from multiple input contexts. In this work, we apply a transformer model to the task of multi-hop question generation without utilizing any sentence-level supporting fact information. We utilize concepts that have proven effective in single-hop question generation, including a copy mechanism and placeholder tokens. We evaluate our model’s performance on the HotpotQA dataset using automated evaluation metrics, including BLEU, ROUGE and METEOR and show an improvement over the previous work. en_US natural language processing question generation machine learning artificial intelligence Natural language processing (Computer science) Computational linguistics Machine learning Artificial intelligence Dissertations, Academic Transformer-based multi-hop question generation Thesis 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 URL http://localhost:4000/bitstreams/8cc28c74-f6d7-4099-b553-8a58a8ac1740/download File MD5 c35128cdb749c419a59aa3bc81a758a6 1464906 application/pdf EMERSON_JOHN_MSC_2022.pdf URL http://localhost:4000/bitstreams/679964ca-3586-40c4-a5c4-3017e7ee8d8a/download File MD5 62b20519fc5cc84b7c107f42a7deef20 146524 text/plain EMERSON_JOHN_MSC_2022.pdf.txt