ISCA Archive Interspeech 2017
ISCA Archive Interspeech 2017

Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification

Bo-Ru Lu, Frank Shyu, Yun-Nung Chen, Hung-Yi Lee, Lin-Shan Lee

Connectionist temporal classification (CTC) is a powerful approach for sequence-to-sequence learning, and has been popularly used in speech recognition. The central ideas of CTC include adding a label “blank” during training. With this mechanism, CTC eliminates the need of segment alignment, and hence has been applied to various sequence-to-sequence learning problems. In this work, we applied CTC to abstractive summarization for spoken content. The “blank” in this case implies the corresponding input data are less important or noisy; thus it can be ignored. This approach was shown to outperform the existing methods in term of ROUGE scores over Chinese Giga-word and MATBN corpora. This approach also has the nice property that the ordering of words or characters in the input documents can be better preserved in the generated summaries.