Learning to Fuse Sentences with Transformers for Summarization
This addresses a specific bottleneck in summarization systems for producing more accurate and concise summaries, but appears incremental as it builds on existing Transformer methods.
The paper tackled the problem of sentence fusion in summarization, where existing systems often produce few or incorrect fusions, and proposed novel Transformer-based algorithms that leverage points of correspondence between sentences, resulting in improved performance as highlighted in experiments.
The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts. However, to date, summarizers can fail on fusing sentences. They tend to produce few summary sentences by fusion or generate incorrect fusions that lead the summary to fail to retain the original meaning. In this paper, we explore the ability of Transformers to fuse sentences and propose novel algorithms to enhance their ability to perform sentence fusion by leveraging the knowledge of points of correspondence between sentences. Through extensive experiments, we investigate the effects of different design choices on Transformer's performance. Our findings highlight the importance of modeling points of correspondence between sentences for effective sentence fusion.