Tracing Mistakes and Finding Gaps in Automatic Word Alignments for Latvian-English Translation
Girgzdis Valdis, Kale Maija, Vaicekauskis Martins, Zarina Ieva, Skadi ncedil a Inguna · Frontiers in artificial intelligence and applications · 2014
This paper aims to contribute to an in-depth understanding of computer based word alignment processes in machine translation (MT). The performance of word alignment, based on IBM models and incorporated in GIZA++, has been widely discussed in machine translation literature. The debate has lead towards a general consensus that GIZA++ does not provide sufficiently good results for word alignments. In this paper, we analyse the performance of GIZA++ and Fast Align for the Latvian-English pair against the manually aligned Gold Standard. Experiments showed that Fast Align proved to be approximately 2–3% more accurate and three times faster than GIZA++ in the alignment task. Where it concerns pre-processing, the removal of articles has a small, but positive, influence on alignment quality and machine translation output. We also present a Word Alignment Visualisation tool for analysis and editing of word alignments.