Parallelization of Maximum Entropy POS Tagging for Bahasa Indonesia with MapReduce
This work addresses efficiency in natural language processing for Bahasa Indonesia, but it is incremental as it applies an existing parallelization method to a specific language task.
The paper tackled the problem of speeding up part-of-speech tagging for Bahasa Indonesia by parallelizing Maximum Entropy training and tagging using MapReduce, resulting in faster tagging times with the fastest achieved using 1,000,000 words and 30 map processes.
In this paper, MapReduce programming model is used to parallelize training and tagging proceess in Maximum Entropy part of speech tagging for Bahasa Indonesia. In training process, MapReduce model is implemented dictionary, tagtoken, and feature creation. In tagging process, MapReduce is implemented to tag lines of document in parallel. The training experiments showed that total training time using MapReduce is faster, but its result reading time inside the process slow down the total training time. The tagging experiments using different number of map and reduce process showed that MapReduce implementation could speedup the tagging process. The fastest tagging result is showed by tagging process using 1,000,000 word corpus and 30 map process.