Abstractive Headline Generation for Spoken Content by Attentive Recurrent Neural Networks with ASR Error Modeling
This addresses the challenge of abstractive summarization for spoken documents, which is incremental as it adapts existing text-based methods to handle ASR errors.
The paper tackled the problem of generating headlines for spoken content by modeling ASR errors within an attentive recurrent neural network, achieving encouraging results that generalize across different speech recognizers.
Headline generation for spoken content is important since spoken content is difficult to be shown on the screen and browsed by the user. It is a special type of abstractive summarization, for which the summaries are generated word by word from scratch without using any part of the original content. Many deep learning approaches for headline generation from text document have been proposed recently, all requiring huge quantities of training data, which is difficult for spoken document summarization. In this paper, we propose an ASR error modeling approach to learn the underlying structure of ASR error patterns and incorporate this model in an Attentive Recurrent Neural Network (ARNN) architecture. In this way, the model for abstractive headline generation for spoken content can be learned from abundant text data and the ASR data for some recognizers. Experiments showed very encouraging results and verified that the proposed ASR error model works well even when the input spoken content is recognized by a recognizer very different from the one the model learned from.