Spans, Not Tokens: A Span-Centric Model for Multi-Span Reading Comprehension

Many questions should be answered by not a single answer but a set of multiple answers. This emerging Multi-Span Reading Comprehension (MSRC) task requires extracting multiple non-contiguous spans from a given context to answer a question. Existing methods extend conventional single-span models to predict the positions of the start and end tokens of answer spans, or predict the beginning-inside-outside tag of each token. Such token-centric paradigms can hardly capture dependencies among span-level answers which are critical to MSRC. In this paper, we propose SpanQualifier, a span-centric scheme where spans, as opposed to tokens, are directly represented and scored to qualify as answers. Explicit span representations enable their interaction which exploits their dependencies to enhance representations. Experiments on three MSRC datasets demonstrate the effectiveness of our span-centric scheme and show that SpanQualifier achieves state-of-the-art results.