• Journal of the Korea Society of Computer and Information
• /
• v.22 no.4
• /
• pp.41-49
• /
• 2017

Word sense disambiguation(WSD) that determines the exact meaning of homonym which can be used in different meanings even in one form is very important to understand the semantical meaning of text document. Many recent researches on WSD have widely used NNLM(Neural Network Language Model) in which neural network is used to represent a document into vectors and to analyze its semantics. Among the previous WSD researches using NNLM, RNN(Recurrent Neural Network) model has better performance than other models because RNN model can reflect the occurrence order of words in addition to the word appearance information in a document. However, since RNN model uses only the forward order of word occurrences in a document, it is not able to reflect natural language's characteristics that later words can affect the meanings of the preceding words. In this paper, we propose a WSD scheme using Bidirectional RNN that can reflect not only the forward order but also the backward order of word occurrences in a document. From the experiments, the accuracy of the proposed model is higher than that of previous method using RNN. Hence, it is confirmed that bidirectional order information of word occurrences is useful for WSD in Korean language.

• Proceedings of the KSPS conference
• /
• 2002.11a
• /
• pp.137-140
• /
• 2002

This study was conducted to examine the korean word length effects on auditory word recognition. Linguistically, word length can be defined by several sublexical units such as letters, phonemes, syllables, and so on. In order to investigate which units are used in auditory word recognition, lexical decision task was used. Experiment 1 and 2 showed that syllable length affected response time, and syllable length interacted with word frequency. As a result, in recognizing auditory word syllable length was important variable.

• Asia Pacific Journal of Corpus Research
• /
• v.1 no.2
• /
• pp.41-56
• /
• 2020

This paper aims to investigate how word order interacts with cliticization in Sakizaya, a Formosan language. This paper looks into nominative and genitive case markers from a corpus-based approach. The data are collected from an online dictionary of Sakizaya, and they are classified into two word orders: nominative case marker preceding genitive case marker and vice versa. The data are also divided into three categories, according to the demarcation of the case markers, which include right, left, or no demarcation. The corpus includes 700 sentences in the construction of predicate + noun phrase + noun phrase. The results suggest that the two case markers tend to be parsed into the preceding word and show right demarcation. The results also reveal that there are type difference and distance effect of the case markers on the cliticization. Nominative case markers show more right demarcation than genitive case markers do in the corpus. Also, the closer the case markers are to the predicate, the more possible the case markers undergo cliticization.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.8
• /
• pp.435-442
• /
• 2008

The n-gram model is appropriate for languages, such as English, in which the word-order is grammatically rigid. However, it is not suitable for Korean in which the word-order is relatively free. Previous work proposed a twoply HMM that reflected the characteristics of Korean but failed to reflect word-order structures among words. In this paper, we define a new segment unit which combines two words in order to reflect the characteristic of word-order among adjacent words that appear in verbal morphemes. Moreover, we propose a two-path language model that estimates probabilities depending on the context based on the proposed segment unit. Experimental results show that the proposed two-path language model yields 25.68% perplexity improvement compared to the previous Korean language models and reduces 94.03% perplexity for the prediction of verbal morphemes where words are combined.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.124-129
• /
• 2006

This parer presents a method of ranking translation word selection for Korean verbs based on lexical knowledge contained in a bilingual Korean-English dictionary and WordNet that are easily obtainable knowledge resources. We focus on deciding which translation of the target word is the most appropriate using the measure of semantic relatedness through the 45 extended relations between possible translations of target word and some indicative clue words that play a role of predicate-arguments in source language text. In order to reduce the weight of application of possibly unwanted senses, we rank the possible word senses for each translation word by measuring semantic similarity between the translation word and its near synonyms. We report an average accuracy of $51\%$ with ten Korean ambiguous verbs. The evaluation suggests that our approach outperforms the default baseline performance and previous works.

• Language and Information
• /
• v.13 no.1
• /
• pp.39-56
• /
• 2009

This paper investigates ordering alternation phenomena in Korean using the dative construction data from Sejong Corpus of Modern Korean (Kim, 2000). The paper first shows that syntactic weight and information structure are distinct and independent factors that influence word order in Korean. Moreover, it reveals that heaviness and givenness compete each other and exert diverging effects on word order, which contrasts the converging effects of these factors shown in word orders of right-branching languages like English. The typological variation of syntactic weight effect poses interesting theoretical and empirical questions, which are discussed in relation to processing efficiency in ordering.

• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.493-501
• /
• 2022

This paper is a study on context-sensitive spelling error correction and uses the Korean WordNet (KorLex)[1] that defines the relationship between words as a graph to improve the performance of the correction[2] based on the vector information of the word embedded in the correction technique. The Korean WordNet replaced WordNet[3] developed at Princeton University in the United States and was additionally constructed for Korean. In order to learn a semantic network in graph form or to use it for learned vector information, it is necessary to transform it into a vector form by embedding learning. For transformation, we list the nodes (limited number) in a line format like a sentence in a graph in the form of a network before the training input. One of the learning techniques that use this strategy is Deepwalk[4]. DeepWalk is used to learn graphs between words in the Korean WordNet. The graph embedding information is used in concatenation with the word vector information of the learned language model for correction, and the final correction word is determined by the cosine distance value between the vectors. In this paper, In order to test whether the information of graph embedding affects the improvement of the performance of context- sensitive spelling error correction, a confused word pair was constructed and tested from the perspective of Word Sense Disambiguation(WSD). In the experimental results, the average correction performance of all confused word pairs was improved by 2.24% compared to the baseline correction performance.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.203-206
• /
• 2001

In the EKMT system, the part of Korea generation makes Korea sentence by using information obtained in the part of transfer. In the case of Korea generation, the conventional EKMT system don't arrange hierarchical word order and performs word order in the only modifier word. This paper proposes Korean adverb odering rule in English-Korean Machine Translation system which generates Korean sentence.

• Phonetics and Speech Sciences
• /
• v.1 no.1
• /
• pp.55-62
• /
• 2009

This paper proposes an improved method to verify a keyword segment that results from a word spotting system. First a baseline word spotting system is implemented. In order to improve performance of the word spotting systems, we use a two-pass structure which consists of a word spotting system and an utterance verification system. Using the basic likelihood ratio test (LRT) based utterance verification system to verify the keywords, there have been certain problems which lead to performance degradation. So, we propose a method which uses phone-level log-likelihood ratios (PLLR) patterns in computing confidence measures for each keyword. The proposed method generates weights according to the PLLR patterns and assigns different weights to each phone in the process of generating confidence measures for the keywords. This proposed method has shown to be more appropriate to word spotting systems and we can achieve improvement in final word spotting accuracy.

• Journal of Korean Medical classics
• /
• v.32 no.1
• /
• pp.61-74
• /
• 2019

Objectives : The purpose of this study is to help select an appropriate word embedding method when analyzing East Asian traditional medicine texts as data. Methods : Based on prescription data that imply traditional methods in traditional East Asian medicine, we have examined 4 count-based word embedding and 2 prediction-based word embedding methods. In order to intuitively compare these word embedding methods, we proposed a "prescription generating game" and compared its results with those from the application of the 6 methods. Results : When the adjacent vectors are extracted, the count-based word embedding method derives the main herbs that are frequently used in conjunction with each other. On the other hand, in the prediction-based word embedding method, the synonyms of the herbs were derived. Conclusions : Counting based word embedding methods seems to be more effective than prediction-based word embedding methods in analyzing the use of domesticated herbs. Among count-based word embedding methods, the TF-vector method tends to exaggerate the frequency effect, and hence the TF-IDF vector or co-word vector may be a more reasonable choice. Also, the t-score vector may be recommended in search for unusual information that could not be found in frequency. On the other hand, prediction-based embedding seems to be effective when deriving the bases of similar meanings in context.