Dialogue Session Segmentation by Embedding-Enhanced TextTiling
Full Text: 1234.PDF
In human-computer conversation systems, the context of a userissued utterance is particularly important because it provides useful background information of the conversation. However, it is unwise to track all previous utterances in the current session as not all of them are equally important. In this paper, we address the problem of session segmentation. We propose an embedding-enhanced TextTiling approach, inspired by the observation that conversation utterances are highly noisy, and that word embeddings provide a robust way of capturing semantics. Experimental results show that our approach achieves better performance than the TextTiling, MMD approaches.
Citation
Y. Song, L. Mou, R. Yan, L. Yi, Z. Zhu, X. Hu. "Dialogue Session Segmentation by Embedding-Enhanced TextTiling". Annual Conference of the International Speech Communication Association, pp 2706–2710, September 2016.| Keywords: | session segmentation, conversation system, word embeddings |
| Category: | In Conference |
| Web Links: | Proceedings |
BibTeX
@incollection{Song+al:INTERSPEECH16,
author = {Yiping Song and Lili Mou and Rui Yan and Li Yi and Zinan Zhu and
Xiaohua Hu},
title = {Dialogue Session Segmentation by Embedding-Enhanced TextTiling},
Pages = {2706–2710},
booktitle = {Annual Conference of the International Speech Communication
Association},
year = 2016,
}Last Updated: February 04, 2021Submitted by Sabina P
