TY - GEN
T1 - Topic embedding of sentences for story segmentation
AU - Yu, Jia
AU - Xiao, Xiong
AU - Xie, Lei
AU - Chng, Eng Siong
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - In this paper, we propose to embed sentences into fixed-dimensional vectors that carry the topic information for story segmentation. As a sentence comprises of a sequence of words and may have different lengths, we use long short-term memory recurrent neural network (LSTM-RNN) to summarize the information of the whole sentence and only predict the topic class at the last word in the sentence. The output of the network at the last word can be used as an embedding of the sentence in the topic space. We used the obtained sentence embeddings in the HMM-based story segmentation framework and obtained promising results. On the TDT2 corpus, the F1 measure is improved to 0.789 from 0.765 which is obtained by a competitive system using DNN and bag-of-words features.
AB - In this paper, we propose to embed sentences into fixed-dimensional vectors that carry the topic information for story segmentation. As a sentence comprises of a sequence of words and may have different lengths, we use long short-term memory recurrent neural network (LSTM-RNN) to summarize the information of the whole sentence and only predict the topic class at the last word in the sentence. The output of the network at the last word can be used as an embedding of the sentence in the topic space. We used the obtained sentence embeddings in the HMM-based story segmentation framework and obtained promising results. On the TDT2 corpus, the F1 measure is improved to 0.789 from 0.765 which is obtained by a competitive system using DNN and bag-of-words features.
UR - http://www.scopus.com/inward/record.url?scp=85044476521&partnerID=8YFLogxK
U2 - 10.1109/APSIPA.2017.8282280
DO - 10.1109/APSIPA.2017.8282280
M3 - 会议稿件
AN - SCOPUS:85044476521
T3 - Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
SP - 1602
EP - 1607
BT - Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
Y2 - 12 December 2017 through 15 December 2017
ER -