• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.504-509
• /
• 2018

Neural machine translation (NMT) has recently achieved the state-of-the-art performance. However, it is reported failing in the word sense disambiguation (WSD) for several popular language pairs. In this paper, we explore the extent to which NMT systems are able to disambiguate the Korean homographs. Homographs, words with different meanings but the same written form, cause the word choice problems for NMT systems. Consistent with the popular language pairs, we discover that NMT systems fail to translate Korean homographs correctly. We provide a Korean word sense disambiguation tool-UTagger to use for improvement of NMT's translation quality. We conducted translation experiments using Korean-English and Korean-Vietnamese language pairs. The experimental results show that UTagger can significantly improve the translation quality of NMT in terms of the BLEU, TER, and DLRATIO evaluation metrics.

• Korean Journal of Cognitive Science
• /
• v.10 no.2
• /
• pp.1-10
• /
• 1999

This paper proposes a noun sense disambiguation method based-on corpus and conceptual information. Previous research has restricted the use of linguistic knowledge to the lexical level. Since knowledge extracted from corpus is stored in words themselves, the methods requires a large amount of space for the knowledge with low recall rate. On the contrary, we resolve noun sense ambiguity by using concept co-occurrence information extracted from an automatically sense-tagged corpus. In one experimental evaluation it achieved, on average, a precision of 82.4%, which is an improvement of the baseline by 14.6%. considering that the test corpus is completely irrelevant to the learning corpus, this is a promising result.

• Journal of the Korean Society for information Management
• /
• v.22 no.2 s.56
• /
• pp.125-145
• /
• 2005

This paper presents a semantic vector space retrieval model incorporating a word sense disambiguation algorithm in an attempt to improve retrieval effectiveness. Nine Korean homonyms are selected for the sense disambiguation and retrieval experiments. The total of approximately 120,000 news articles comprise the raw test collection and 18 queries including homonyms as query words are used for the retrieval experiments. A Naive Bayes classifier and EM algorithm representing supervised and unsupervised learning algorithms respectively are used for the disambiguation process. The Naive Bayes classifier achieved $92\%$ disambiguation accuracy. while the clustering performance of the EM algorithm is $67\%$ on the average. The retrieval effectiveness of the semantic vector space model incorporating the Naive Bayes classifier showed $39.6\%$ precision achieving about $7.4\%$ improvement. However, the retrieval effectiveness of the EM algorithm-based semantic retrieval is $3\%$ lower than the baseline retrieval without disambiguation. It is worth noting that the performances of disambiguation and retrieval depend on the distribution patterns of homonyms to be disambiguated as well as the characteristics of queries.

• The Journal of the Korea Contents Association
• /
• v.16 no.4
• /
• pp.418-425
• /
• 2016

This paper presents the part-of-speech set which is highly efficient at knowledge-based word sense disambiguation for Korean nouns. 174,000 sentences extracted for test set from Sejong semantic tagged corpus whose sense is based on Standard korean dictionary. We disambiguate selected nouns in test set using glosses and examples in Standard Korean dictionary. 15 part-of-speeches which give the best performance for all test set and 17 part-of-speeches which give the best performance for accuracy average of selected nouns are selected. We obtain 12% more performance by those part-of-speech sets than by full 45 part-of-speech set.

• Journal of the Korean Society for information Management
• /
• v.24 no.1 s.63
• /
• pp.321-342
• /
• 2007

This study presents an effective word sense disambiguation model that does not require manual sense tagging Process by automatically tagging the right sense using a machine-readable and the collocation co-occurrence-based methods. The dictionary information-based method that applied multiple feature selection showed the tagging accuracy of 70.06%, and the collocation co-occurrence-based method 56.33%. The sense classifier using the dictionary information-based tagging method showed the classification accuracy of 68.11%, and that using the collocation co-occurrence-based tagging method 62.09% The combined 1a99ing method applying data fusion technique achieved a greater performance of 76.09% resulting in the classification accuracy of 76.16%.

• Korean Journal of Cognitive Science
• /
• v.27 no.1
• /
• pp.43-60
• /
• 2016

Recently, Unsupervised Word Sense Disambiguation research has focused on Graph based disambiguation. Graph-based disambiguation has built a semantic graph based on words collocated in context or sentence. However, building such a graph over all ambiguous word lead to unnecessary addition of edges and nodes (and hence increasing the error). In contrast, our work uses Word2Vec to consider the most similar words to an ambiguous word in the context or sentences, to rebuild a graph of the matched words. As a result, we show a higher F1-Measure value than the previous methods by using Word2Vec.

• KIISE Transactions on Computing Practices
• /
• v.22 no.2
• /
• pp.107-112
• /
• 2016

The Sejong Electronic(machine-readable) Dictionary, developed by the 21st century Sejong Plan, contains systematically organized information on Korean words. It helps to solve problems encountered in the electronic formatting of the still-commonly-used hard-copy dictionary. The Sejong Electronic Dictionary, however has a limitation relate to sentence structure and selection-restricted nouns. This paper discuses the limitations of word-sense disambiguation(WSD) that uses subcategorization information suggested by the Sejong Electronic Dictionary and generalized selection-restricted nouns from the Korean Lexico-semantic network. An alternative method that utilized semi-supervised learning, the chi-square test and some other means to make WSD decisions is presented herein.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.747-751
• /
• 2010

This paper proposes the method that increases the accuracy for tagging word meaning by creating sense tagged data automatically using machine readable dictionaries. The concept of meaning group is applied here, where the meaning group for each meaning of a target word consists of neighbor words of the target word. To enhance the tagging accuracy, the notion of concentration is used for the weight of each word in a meaning group. The tagging result in SENSEVAL-2 data shows that accuracy of the proposed method is better than that of existing ones.

• 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.

• Journal of Information Management
• /
• v.42 no.2
• /
• pp.193-210
• /
• 2011

The study was applied to context window sizes and weighting method to obtain the best performance of word sense disambiguation using support vector machine. The context window sizes were used to a 3-word, sentence, 50-bytes, and document window around the targeted word. The weighting methods were used to Binary, Term Frequency(TF), TF ${\times}$ Inverse Document Frequency(IDF), and Log TF ${\times}$ IDF. As a result, the performance of 50-bytes in the context window size was best. The Binary weighting method showed the best performance.