eprintid: 2687
rev_number: 7
eprint_status: archive
userid: 290
dir: disk0/00/00/26/87
datestamp: 2017-11-27 04:29:34
lastmod: 2017-11-27 04:29:34
status_changed: 2017-11-27 04:29:34
type: conference_item
metadata_visibility: show
creators_name: Ngo, Thi Lan
creators_name: Pham, Bao Son
creators_name: Pham, Khac Linh
creators_name: Phan, Xuan Hieu
creators_name: Cao, Minh Son
creators_id: sonpb@vnu.edu.vn
creators_id: hieupx@vnu.edu.vn
title: Dialogue act segmentation for Vietnamese human-human conversational texts
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: Dialog act identification plays an important role in understanding conversations. It has been widely applied in many fields such as dialogue systems, automatic machine translation, automatic speech recognition, and especially useful in systems with human-computer natural language dialogue interfaces such as virtual assistants and chatbots. The first step of identifying dialog act is identifying the boundary of the dialog act in utterances. In this paper, we focus on segmenting the utterance according to the dialog act boundaries, i.e. functional segments identification, for Vietnamese utterances. We investigate carefully functional segment identification in two approaches: (1) machine learning approach using maximum entropy (ME) and conditional random fields (CRFs); (2) deep learning approach using bidirectional Long Short-Term Memory (LSTM) with a CRF layer (Bi-LSTM-CRF) on two different conversational datasets: (1) Facebook messages (Message data); (2) transcription from phone conversations (Phone data). To the best of our knowledge, this is the first work that applies deep learning based approach to dialog act segmentation. As the results show, deep learning approach performs appreciably better as to compare with traditional machine learning approaches. Moreover, it is also the first study that tackles dialog act and functional segment identification for Vietnamese.
date: 2017-10-19
date_type: published
official_url: http://kse2017.dhsphue.edu.vn
full_text_status: none
pres_type: paper
pagerange: 203-208
event_title: The 9th International Conference on Knowledge and Systems Engineering (KSE 2017)
event_location: Hue city, Vietnam
event_dates: October 19-21, 2017
event_type: conference
refereed: TRUE
related_url_url: http://ieeexplore.ieee.org/document/8119459/
related_url_type: pub
funders: Vietnam National University, Hanoi (VNU)
projects: VNU Project No. QG.15.29
citation:   Ngo, Thi Lan and Pham, Bao Son and Pham, Khac Linh and Phan, Xuan Hieu and Cao, Minh Son  (2017) Dialogue act segmentation for Vietnamese human-human conversational texts.  In: The 9th International Conference on Knowledge and Systems Engineering (KSE 2017), October 19-21, 2017, Hue city, Vietnam.