期刊论文、会议论文

Yan, Rui

英文

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

2308-457X

2016

08-12-September-2016

2706-2710

17th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2016)

Interspeech

SEP 08-12, 2016

San Francisco, CA

[Song, Yiping;Mou, Lili;Yan, Rui;Zhang, Ming] Peking Univ, Beijing, Peoples R China.^[Mou, Lili] Peking Univ, MoE, Key Lab High Confidence Software Technol, Beijing, Peoples R China.^[Yan, Rui] Baidu Inc, Nat Language Proc Dept, Beijing, Peoples R China.^[Yan, Rui;Yi, Li;Zhu, Zinan;Hu, Xiaohua] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.

apple, amazon alexa, Google, Microsoft, ebay, facebook, YAHOO JAPAN, Baidu Res, IBM Res, CIRRUS LOGIC, DATATANG, NUANCE, Speechocean Ltd, Yandex, Raytheon Technol

C/O EMMANUELLE FOXONET, 4 RUE DES FAUVETTES, LIEU DIT LOUS TOURILS, BAIXAS, F-66390, FRANCE

ISCA-INT SPEECH COMMUNICATION ASSOC

978-1-5108-3313-5

10.21437/Interspeech.2016-1234

National Natural Science Foundation of China (NSFC Grant)National Natural Science Foundation of China (NSFC) [61272343, 61472006]; Doctoral Program of Higher Education of ChinaSpecialized Research Fund for the Doctoral Program of Higher Education (SRFDP) [20130001110032]; National Basic Research Program (973 Program)National Basic Research Program of China [2014CB340405]

本校为通讯机构

In human-computer conversation systems, the context of a user-issued 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 approac...