An Automatic Korean Word Spacing System for Devices with Low Computing Power

Balanced Korean Word Spacing with Structural SVM

Most studies on statistical Korean word spacing do not utilize the information provided by the input sentence and assume that it was completely concatenated. This makes the word spacer ignore the correct spaced parts of the input sentence and erroneously alter them. To overcome such limit, this paper proposes a structural SVM-based Korean word spacing method that can utilize the space informati...

‏‎design of an analog ram (aram)chip with 10-bit resolution and low-power for signal processing in 0/5m cmos process‎‏

برای پردازش سیگنال آنالوگ در شبکه های عصبی ، معمولا نیاز به یک واحد حافظه آنالوگ احساس میشود که بدون احتیاج به ‏‎a/d‎‏ و‏‎d/a‎‏ بتواند بطور قابل انعطاف و مطمئن اطلاعات آنالوگ را در خود ذخیره کند. این واحد حافظه باید دارای دقت کافی ، سرعت بالا ، توان تلفاتی کم و سایز کوچک باشد و همچنین اطلاعات را برای زمان کافی در خود نگهدارد. برای پیاده سازی سیستمی که همه این قابلیتها را در خود داشته باشد، کوشش...

Automatic Word Spacing Using Hidden Markov Model for Refining Korean Text Corpora

This paper proposes a word spacing model using a hidden Markov model (HMM) for re ning Korean raw text corpora. Previous statistical approaches for automatic word spacing have used models that make use of inaccurate probabilities because they do not consider the previous spacing state. We consider word spacing problem as a classi cation problem such as Part-of-Speech (POS) tagging and have expe...

A Novel Discriminative Probabilistic Model for Automatic Word Spacing on Mobile Devices

This paper presents a new method for automatic word spacing in Korean. Our major challenge is to reduce the memory usage and processing time to be suitable for mobile devices while ensuring a high performance. Since mobile devices are more difficult to type letters into than general PCs with current technology, spacing errors such as writing with no spaces can occur relatively frequently in mob...

Automatic Word Spacing Using Hidden Markov Model