An end-to-end neural network approach to story segmentation

Jia Yu, Lei Xie, Xiong Xiao, Eng Siong Chng

科研成果: 书/报告/会议事项章节会议稿件同行评审

2 引用 (Scopus)

摘要

This paper proposes an end-to-end story segmentation approach based on long short-term memory (LSTM) - recurrent neural network (RNN). Traditional story segmentation approaches are a two-stage pipeline consisting of feature extraction and segmentation, each of which has its individual objective function. In other words, the objective function used to extract features is different from the true performance measure of story segmentation, which may degrade the segmentation results. In this paper, we combine the two components and optimize them jointly, using an LSTM-RNN. Specifically, one LSTM layer is used to extract sentence vectors, and another LSTM layer is used to predict story boundaries by taking as input of the sentence vectors. Importantly, the whole network is optimized directly to predict story boundaries. We also investigate bi-directional LSTM (BLSTM) that can utilize past and future information in the process of extracting sentence vectors and story boundary prediction. Experimental results on the TDT2 corpus show that the proposed approach achieves state-of-the-art performance in story segmentation.

源语言英语
主期刊名Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
出版商Institute of Electrical and Electronics Engineers Inc.
171-176
页数6
ISBN(电子版)9781538615423
DOI
出版状态已出版 - 2 7月 2017
活动9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, 马来西亚
期限: 12 12月 201715 12月 2017

出版系列

姓名Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
2018-February

会议

会议9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
国家/地区马来西亚
Kuala Lumpur
时期12/12/1715/12/17

指纹

探究 'An end-to-end neural network approach to story segmentation' 的科研主题。它们共同构成独一无二的指纹。

引用此