A Method to Overcome the Ambiguities in Shallow Parse and Transfer Machine Translation

Authors

  • Jernej Vičič University of Primorska, Andrej Marušič Institute (UP IAM), Muzejski trg 2, 6000 Koper
  • Marko Grgurovič University of Primorska, The Andrej Marušič Institute, Muzejski trg 2, 6000 Koper

Keywords:

Multigraph, k-shortest paths, shallow parse and transfer RBMT, machine translation

Abstract

The manuscript proposes a new architecture for a Shallow Parsing and Shallow Transfer Rule-Based Machine Translation System. The newly proposed architecture omits the disambiguation module in the starting phases of the translation pipeline and stores all translation candidates generated by the ambiguous process in the morphological analysis phase. The architecture is based on multigraphs. We propose a simplified version of k-best shortest path algorithm for this special case of directed multigraph. The k-best set is ranked using a trigram language model. The empirical evaluation shows that the new architecture produces better translation quality results with constant delay in time.

Downloads

Download data is not yet available.

Author Biography

Jernej Vičič, University of Primorska, Andrej Marušič Institute (UP IAM), Muzejski trg 2, 6000 Koper

Research associate at the UPIAM, University of Primorska Assistant professor at the FAMNIT, University of Primorska, Department of Information Sciences and Technology

Downloads

Published

2019-02-04

How to Cite

Vičič, J., & Grgurovič, M. (2019). A Method to Overcome the Ambiguities in Shallow Parse and Transfer Machine Translation. Computing and Informatics, 37(6), 1443–1463. Retrieved from http://147.213.75.17/ojs/index.php/cai/article/view/2018_6_1443