Paper: An Efficient Two-Pass Approach to Synchronous-CFG Driven Statistical MT

ACL ID N07-1063
Title An Efficient Two-Pass Approach to Synchronous-CFG Driven Statistical MT
Venue Human Language Technologies
Session Main Conference
Year 2007
Authors

We present an efficient, novel two-pass approach to mitigate the computational impact resulting from online intersection of an n-gram language model (LM) and a probabilistic synchronous context-free grammar (PSCFG) for statistical machine translation. In first pass CYK-style decod- ing, we consider first-best chart item ap- proximations, generating a hypergraph of sentence spanning target language deriva- tions. In the second stage, we instantiate specific alternative derivations from this hypergraph, using the LM to drive this search process, recovering from search er- rors made in the first pass. Model search errors in our approach are comparable to those made by the state-of-the-art “Cube Pruning” approach in (Chiang, 2007) un- der comparable pruning conditions evalu- atedonbothhier...