Structure-Infused Copy Mechanisms for Abstractive Summarization
This addresses the issue of meaning preservation in abstractive summarization for NLP applications, but it is incremental as it builds on existing copy mechanisms.
The paper tackled the problem of abstractive summarization systems missing important words and relations from source sentences by introducing structure-infused copy mechanisms that incorporate source dependency structure. The approach demonstrated effectiveness and compared favorably to state-of-the-art methods.
Seq2seq learning has produced promising results on summarization. However, in many cases, system summaries still struggle to keep the meaning of the original intact. They may miss out important words or relations that play critical roles in the syntactic structure of source sentences. In this paper, we present structure-infused copy mechanisms to facilitate copying important words and relations from the source sentence to summary sentence. The approach naturally combines source dependency structure with the copy mechanism of an abstractive sentence summarizer. Experimental results demonstrate the effectiveness of incorporating source-side syntactic information in the system, and our proposed approach compares favorably to state-of-the-art methods.