Automatic word spacing of erroneous sentences in mobile devices with limited hardware resources

Song, Yeongkil; Kim, Harksoo

doi:10.1016/j.ipm.2010.11.004

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Is the father in a room?). " However, in information appliances with a small main memory, it is impractical to use earlier statistical models based on character bigrams or longer combinations because they require a large amount of memory for loading the statistical information [15][16][17]. The number of characters that are often used in modern Korean is about 10 4 , which implies that the number of character bigrams reaches 10 8 .…”

Section: Previous Workmentioning

confidence: 99%

“…To overcome this problem, Park et al [18] proposed a combined model of rule-based and memory-based learning. Song and Kim [15] combined character unigram statistics and error-correction rules of character bigrams or longer combinations. Kim et al [16, 17] proposed a modified HMM that uses probabilities of word spacing patterns as observation probabilities.…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Lightweight Word Spacing Model Based on Short Text Messages for Social Networking in Smart Homes

Song

Kim

2014

International Journal of Distributed Sensor Networks

Self Cite

View full text Add to dashboard Cite

In smart homes, information appliances interact with residents via social network services. To capture residents' intentions, the information appliances should analyze short text messages entered typically through small mobile devices. However, most information appliances have hardware constraints such as small memory, limited battery capacity, and restricted processing power. Therefore, it is not easy to embed intelligent applications based on natural language processing (NLP) techniques, which traditionally require large memory and high-end processing power, into information appliances. To overcome this problem, lightweight NLP modules should be implemented. We propose an automatic word spacing system, the first step module of NLP for many languages with their own word spacing rules, which is designed for information appliances with limited hardware resources. The proposed system consists of a word spacing dictionary and a pattern-matching module. When a sentence is entered, the pattern-matching module inserts spaces by simply looking up the word spacing dictionary in a back-off manner. In comparative experiments with previous models, the proposed method showed low memory usage (0.79 MB) and high character-unit accuracy (0.9460) without requiring complex arithmetical computations. On the basis of these experiments, we conclude that the proposed system is suitable for information appliances with many hardware limitations.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%