2021/12/02 by Jia-Yan Wu, Jiayan Wu, Wu, Jia-Yan +7 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Software Engineering Research #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2112.01332
openalex publication_date 2021/12/02 · openalex created_date 2021/12/06 · arxiv created 2021/12/09 · arxiv updated 2021/12/10 · openalex updated_date 2026/07/28
Machine-generated citation sentences can aid automated scientific literature review and assist article writing. Current methods in generating citation text were limited to single citation generation using the citing document and a cited document as input. However, in real-world situations, writers often summarize several studies in one sentence or discuss relevant information across the entire paragraph. In addition, multiple citation intents have been previously identified, implying that writers may need control over the intents of generated sentences to cover different scenarios. Therefore, this work focuses on generating multiple citations and releasing a newly collected dataset named CiteMI to drive the future research. We first build a novel generation model with the Fusion-in-Decoder approach to cope with multiple long inputs. Second, we incorporate the predicted citation intents into training for intent control. The experiments demonstrate that the proposed approaches provide much more comprehensive features for generating citation sentences.