Towards Generating Citation Sentences for Multiple References with Intent Control
This work addresses the need for automated tools to assist in scientific writing by enabling multi-citation summarization with controlled intents, representing an incremental advancement over single-citation methods.
The paper tackles the problem of generating citation sentences for multiple references with intent control, and the result is a new dataset (CiteMI) and a model that provides more comprehensive features for generating such sentences.
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.