eprintid: 3041
rev_number: 9
eprint_status: archive
userid: 244
dir: disk0/00/00/30/41
datestamp: 2018-08-03 15:41:57
lastmod: 2018-08-03 15:41:57
status_changed: 2018-08-03 15:41:57
type: conference_item
metadata_visibility: show
creators_name: Nguyen, Ngoc Khuong
creators_name: Le, Anh Cuong
creators_name: Nguyen, Viet Ha
creators_id: cuongla@vnu.edu.vn
creators_id: hanv@vnu.edu.vn
title: An Attention-Based Long-Short-Term-Memory Model for Paraphrase Generation
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: Neural network based sequence-to-sequence models have shown to be the effective approach for paraphrase generation. In the problem of paraphrase generation, there are some words which should be ignored in the target text generation. The current models do not pay enough attention to this problem. To overcome this limitation, in this paper we propose a new model which is a penalty coefficient attention-based Residual Long-Short-Term-Memory (PCA-RLSTM) neural network for forming an end-to-end paraphrase generation model. Extensive experiments on the two most popular corpora (PPDB and WikiAnswers) show that our proposed model’s performance is better than the state-of-the-art models for paragraph generation problem.
date: 2018
date_type: completed
official_url: https://link.springer.com/chapter/10.1007%2F978-3-319-75429-1_14
full_text_status: none
pres_type: paper
pagerange: 166-178
event_title: IUKM 2018
event_dates: 04 February 2018
event_type: conference
refereed: TRUE
citation:   Nguyen, Ngoc Khuong and Le, Anh Cuong and Nguyen, Viet Ha  (2018) An Attention-Based Long-Short-Term-Memory Model for Paraphrase Generation.  In: IUKM 2018, 04 February 2018.