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

TL;DR

This paper introduces a novel abstractive summarization method for spoken content using Connectionist Temporal Classification (CTC), which effectively handles noisy data and preserves input order, outperforming existing methods on Chinese corpora.

Contribution

The work applies CTC to spoken content summarization, demonstrating improved ROUGE scores and better order preservation compared to prior approaches.

Findings

Outperforms existing methods on Chinese Gigaword and MATBN corpora.

Preserves input word or character order in summaries.

Handles noisy or less important input data effectively.

Abstract

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.