Work

Exact Decoding of Phrase-based Translation Models through Lagrangian Relaxation

Year: 2011

Type: dissertation

Abstract: This paper describes an algorithm for exact decoding of phrase-based translation models, based on Lagrangian relaxation. The method recovers exact solutions, with certificates of optimality, on over 99 % of test examples. The method is much more efficient than approaches based on linear programming (LP) or integer linear programming (ILP) solvers: these methods are not feasible for anything other than short sentences. We compare our method to MOSES (Koehn et al., 2007), and give precise estimates of the number and magnitude of search errors that MOSES makes.

Source: DSpace@MIT (Massachusetts Institute of Technology)

Authors: Yin-wen Chang, Michael Collins

Institutions: MIT Computer Science and Artificial Intelligence Laboratory, Columbia University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2149192313

Cites: 27

Cited by: 45

Related to: 10