Extraction Meets Abstraction: Ideal Answer Generation for Biomedical Questions

Abstract

The growing number of biomedical publications is a challenge for human researchers, who invest considerable effort to search for relevant documents and pinpointed answers. Biomedical Question Answering can automatically generate answers for a user's topic or question, significantly reducing the effort required to locate the most relevant information in a large document corpus. Extractive summarization techniques, which concatenate the most relevant text units drawn from multiple documents, perform well on automatic evaluation metrics like ROUGE, but score poorly on human readability, due to the presence of redundant text and grammatical errors in the answer. This work moves toward abstractive summarization, which attempts to distill and present the meaning of the original text in a more coherent way. We incorporate a sentence fusion approach, based on Integer Linear Programming, along with three novel approaches for sentence ordering, in an attempt to improve the human readability of ideal answers. Using an open framework for configuration space exploration (BOOM), we tested over 2000 unique system configurations in order to identify the best-performing combinations for the sixth edition of Phase B of the BioASQ challenge.

Classification Betters Regression in Query-based Multi-document Summarisation Techniques for Question Answering: Macquarie University at BioASQ7b

“…Extractive Approaches [7] (none) Regression & Reinforcement Learning [4] Fusion Maximum Marginal Relevance [1] (none) Lexical chains [9] Fine-tuned Pointer Generator Coverage Learning to rank…”

“…Fig. 3 shows the scatterplots of ROUGE-SU4 recall, precision and F1 with respect to the average human evaluation 4 . We observe that the relation between ROUGE and the human evaluations is not linear, and that Precision and F1 have a clear correlation.…”