Automatic community creation for abstractive spoken conversation summarization

Abstract

Summarization of spoken conversations is a challenging task, since it requires deep understanding of dialogs. Abstractive summarization techniques rely on linking the summary sentences to sets of original conversation sentences, i.e. communities. Unfortunately, such linking information is rarely available or requires trained annotators. We propose and experiment automatic community creation using cosine similarity on different levels of representation: Raw text, WordNet SynSet IDs, and word embeddings. We show that the abstractive summarization systems with automatic communities significantly outperform previously published results on both English and Italian corpora.