• Language and Information
• /
• v.7 no.2
• /
• pp.103-115
• /
• 2003

In recent years, many organizations have been constructing their own large corpora to achieve corpus representativeness. However, there is no reliable guideline as to how large corpus resources should be compiled, especially for Korean corpora. In this study, we have contrived a new statistical model, ARIMA (Autoregressive Integrated Moving Average), for predicting the relationship between linguistic items (the number of types) and corpus size (the number of tokens), overcoming the major flaws of several previous researches on this issue. Finally, we shall illustrate that the ARIMA model presented is valid, accurate and very reliable. We are confident that this study can contribute to solving some inherent problems of corpus linguistics, such as corpus predictability, corpus representativeness and linguistic comprehensiveness.

• Phonetics and Speech Sciences
• /
• v.6 no.3
• /
• pp.155-164
• /
• 2014

This paper proposes a new method to determine the recognition units for large vocabulary continuous speech recognition (LVCSR) in Korean by applying unsupervised segmentation and merging. In the proposed method, a text sentence is segmented into morphemes and position information is added to morphemes. Then submorpheme units are obtained by splitting the morpheme units through the maximization of posterior probability terms. The posterior probability terms are computed from the morpheme frequency distribution, the morpheme length distribution, and the morpheme frequency-of-frequency distribution. Finally, the recognition units are obtained by sequentially merging the submorpheme pair with the highest frequency. Computer experiments are conducted using a Korean LVCSR with a 100k word vocabulary and a trigram language model obtained by a 300 million eojeol (word phrase) corpus. The proposed method is shown to reduce the out-of-vocabulary rate to 1.8% and reduce the syllable error rate relatively by 14.0%.

• Phonetics and Speech Sciences
• /
• v.10 no.4
• /
• pp.111-119
• /
• 2018

This paper proposes a method to improve speech recognition performance by extracting various pronunciations of the pseudo-morpheme unit from an eojeol unit corpus and generating a new recognition unit considering pronunciation variations. In the proposed method, we first align the pronunciation of the eojeol units and the pseudo-morpheme units, and then expand the pronunciation dictionary by extracting the new pronunciations of the pseudo-morpheme units at the pronunciation of the eojeol units. Then, we propose a new recognition unit that relies on pronunciation by tagging the obtained phoneme symbols according to the pseudo-morpheme units. The proposed units and their extended pronunciations are incorporated into the lexicon and language model of the speech recognizer. Experiments for performance evaluation are performed using the Korean speech recognizer with a trigram language model obtained by a 100 million pseudo-morpheme corpus and an acoustic model trained by a multi-genre broadcast speech data of 445 hours. The proposed method is shown to reduce the word error rate relatively by 13.8% in the news-genre evaluation data and by 4.5% in the total evaluation data.

• Korean Journal of Cognitive Science
• /
• v.17 no.4
• /
• pp.303-321
• /
• 2006

According to Harris'(1966) distributional hypothesis, understanding the meaning of a word is thought to be dependent on its context. Under this hypothesis about human language ability, this paper proposes a computational model for native speaker's language processing mechanism concerning word sense disambiguation, based on two sets of experiments. Among the three computational models discussed in this paper, namely, the logic model, the probabilistic model, and the probabilistic inference model, the experiment shows that the logic model is first applied fer semantic disambiguation of the key word. Nexr, if the logic model fails to apply, then the probabilistic model becomes most relevant. The three models were also compared with the test results in terms of Pearson correlation coefficient value. It turns out that the logic model best explains the human decision behaviour on the ambiguous words, and the probabilistic inference model tomes next. The experiment consists of two pans; one involves 30 sentences extracted from 1 million graphic-word corpus, and the result shows the agreement rate anong native speakers is at 98% in terms of word sense disambiguation. The other pm of the experiment, which was designed to exclude the logic model effect, is composed of 50 cleft sentences.