Date of Original Version

10-2012

Type

Article

Journal Title

Prague Bulletin of Mathematical Linguistics

Volume

98

First Page

51

Last Page

61

Rights Management

© 2012 PBML

Abstract or Description

This paper describes pycdec, a Python module for the cdec decoder. It enables Python code to use cdec's fast C++ implementation of core finite-state and context-free inference algorithms for decoding and alignment. The high-level interface allows developers to build integrated MT applications that take advantage of the rich Python ecosystem without sacrificing computational performance. We give examples of how to interact directly with the main cdec data structures (lattices, hypergraphs, sparse feature vectors), evaluate translation quality, and use the suffix-array grammar extraction code. This permits rapid prototyping of new algorithms for training, data visualization, and utilizing MT and related structured prediction tasks.

DOI

10.2478/v10108-012-0008-7

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Share

COinS
 

Published In

Prague Bulletin of Mathematical Linguistics, 98, 51-61.