Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification
This work addresses the problem of generating summaries from spoken content while preserving word order, which is incremental as it adapts an existing method to a new application.
The paper tackled abstractive summarization for spoken content by applying Connectionist Temporal Classification (CTC), which outperformed existing methods with higher ROUGE scores on Chinese Gigaword and MATBN corpora.
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 Gigaword 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.