An important problem when using Stochastic Inversion Transduction Grammars is their computational cost. More specifically, when dealing with corpora such as Europarl only one iteration of the estimation algorithm becomes prohibitive. In this work, we apply a reduction of the cost by taking profit of the bracketing information in parsed corpora and show machine translation results obtained with a bracketed Europarl corpus, yielding interresting improvements when increasing the number of non-terminal symbols.
机构:
Yale Univ, Dept Mech Engn, New Haven, CT 06520 USA
Washington Univ, Dept Energy Environm & Chem Engn, St Louis, MO USAYale Univ, Dept Mech Engn, New Haven, CT 06520 USA
Hogan, Christopher J., Jr.
Li, Lin
论文数: 0引用数: 0
h-index: 0
机构:
Washington Univ, Dept Energy Environm & Chem Engn, St Louis, MO USAYale Univ, Dept Mech Engn, New Haven, CT 06520 USA
Li, Lin
Chen, Da-ren
论文数: 0引用数: 0
h-index: 0
机构:
Washington Univ, Dept Energy Environm & Chem Engn, St Louis, MO USAYale Univ, Dept Mech Engn, New Haven, CT 06520 USA
Chen, Da-ren
Biswas, Pratim
论文数: 0引用数: 0
h-index: 0
机构:
Washington Univ, Dept Energy Environm & Chem Engn, St Louis, MO USAYale Univ, Dept Mech Engn, New Haven, CT 06520 USA