Please use this identifier to cite or link to this item:
Appears in Collections:Literature and Languages Conference Papers and Proceedings
Peer Review Status: Refereed
Author(s): Wang, Longyue
Zhang, Xiaojun
Tu, Zhaopeng
Li, Hang
Liu, Qun
Contact Email:
Title: Dropped Pronoun Generation for Dialogue Machine Translation
Citation: Wang L, Zhang X, Tu Z, Li H & Liu Q (2016) Dropped Pronoun Generation for Dialogue Machine Translation. In: 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing Proceedings. 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), Shanghai, China, 20.03.2016-25.03.2016. Danvers, MA USA: IEEE, pp. 6110-6114.
Issue Date: 1-Mar-2016
Date Deposited: 30-Jun-2016
Conference Name: 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016)
Conference Dates: 2016-03-20 - 2016-03-25
Conference Location: Shanghai, China
Abstract: Dropped pronoun (DP) is a common problem in dialogue machine translation, in which pronouns are frequently dropped in the source sentence and thus are missing in its translation. In response to this problem, we propose a novel approach to improve the translation of DPs for dialogue machine translation. Firstly, we build a training data for DP generation, in which the DPs are automatically added according to the alignment information from a parallel corpus. Then we model the DP generation problem as a sequence labelling task, and develop a generation model based on recurrent neural networks and language models. Finally, we apply the DP generator to machine translation task by completing the source sentences with the missing pronouns. Experimental results show that our approach achieves a significant improvement of 1.7 BLEU points by recalling possible DPs in the source sentences.
Status: VoR - Version of Record
Rights: The publisher does not allow this work to be made publicly available in this Repository. Please use the Request a Copy feature at the foot of the Repository record to request a copy directly from the author. You can only request a copy if you wish to use this work for your own research or private study.
Licence URL(s):

Files in This Item:
File Description SizeFormat 
0006110.pdfFulltext - Published Version405.29 kBAdobe PDFUnder Embargo until 2999-12-02    Request a copy

Note: If any of the files in this item are currently embargoed, you can request a copy directly from the author by clicking the padlock icon above. However, this facility is dependent on the depositor still being contactable at their original email address.

This item is protected by original copyright

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved

If you believe that any material held in STORRE infringes copyright, please contact providing details and we will remove the Work from public display in STORRE and investigate your claim.