Paper Info
Title
Leveraging bilingually-constrained synthetic data via multi-task neural networks for implicit discourse relation recognition.
Abstract
Recognizing implicit discourse relations is an important but challenging task in discourse understanding. To alleviate the shortage of labeled data, previous work automatically generates synthetic implicit data (SynData) as additional training data, by removing connectives from explicit discourse instances. Although SynData has been proven useful for implicit discourse relation recognition, it also has the meaning shift problem and the domain problem. In this paper, we first propose to use bilingually-constrained synthetic implicit data (BiSynData) to enrich the training data, which can alleviate the drawbacks of SynData. Our BiSynData is constructed from a bilingual sentence-aligned corpus according to the implicit/explicit mismatch between different languages. Then we design a multi-task neural network model to incorporate our BiSynData to benefit implicit discourse relation recognition. Experimental results on both the English PDTB and Chinese CDTB data sets show that our proposed method achieves significant improvements over baselines using SynData.
Year
DOI
Venue
2017
10.1016/j.neucom.2017.02.084
Neurocomputing
Keywords
Field
DocType
Bilingually-constrained synthetic implicit data,Multi-task learning,Implicit discourse relation recognition,Neural network
Training set,Discourse relation,Data set,Multi-task learning,Computer science,Synthetic data,Natural language processing,Artificial intelligence,Labeled data,Artificial neural network,Economic shortage,Machine learning
Journal
Volume
Issue
ISSN
243
C
0925-2312
Citations 
PageRank 
References 
1
0.36
30
Authors
5
Name
Order
Citations
PageRank
ChangXing Wu172.11
Xiaodong Shi282.16
CHEN Yi-dong310627.34
Yanzhou Huang472.16
Jinsong Su526041.51