• MALSORI
• /
• v.55
• /
• pp.103-118
• /
• 2005

In this paper, we describe a morpheme-based pronunciation lexicon useful for Korean LVCSR. The phonemic-context-dependent multiple pronunciation lexicon improves the recognition accuracy when cross-morpheme pronunciation variations are distinguished from within-morpheme pronunciation variations. Since adding all possible pronunciation variants to the lexicon increases the lexicon size and confusability between lexical entries, we have developed a lexicon pruning scheme for optimal selection of pronunciation variants to improve the performance of Korean LVCSR. By building a proposed pronunciation lexicon, an absolute reduction of $0.56\%$ in WER from the baseline performance of $27.39\%$ WER is achieved by cross-morpheme pronunciation variations model with a phonemic-context-dependent multiple pronunciation lexicon. On the best performance, an additional reduction of the lexicon size by $5.36\%$ is achieved from the same lexical entries.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.9
• /
• pp.4264-4279
• /
• 2017

In this paper, maximum likelihood-based automatic lexicon generation using mixed-syllables is proposed for unlimited vocabulary voice interface for East Asian languages (e.g. Korean, Chinese and Japanese) in AI-assistant based interaction with mobile devices. The conventional lexicon has two inevitable problems: 1) a tedious repetition of out-of-lexicon unit additions to the lexicon, and 2) the propagation of errors during a morpheme analysis and space segmentation. The proposed method provides an automatic framework to solve the above problems. The proposed method produces a level of overall accuracy similar to one of previous methods in the presence of one out-of-lexicon word in a sentence, but the proposed method provides superior results with the absolute improvements of 1.62%, 5.58%, and 10.09% in terms of word accuracy when the number of out-of-lexicon words in a sentence was two, three and four, respectively.

• Proceedings of the KSPS conference
• /
• 2006.11a
• /
• pp.24-27
• /
• 2006

This paper describes how a domain dependent pronunciation lexicon is generated and optimized for Korean large vocabulary continuous speech recognition(LVCSR). At the level of lexicon, pronunciation variations are usually modeled by adding pronunciation variants to the lexicon. We propose the criteria for selecting appropriate pronunciation variants in lexicon: (i) likelihood and (ii) frequency factors to select variants. Our experiment is conducted in three steps. First, the variants are generated with knowledge-based rules. Second, we generate a domain dependent lexicon which includes various numbers of pronunciation variants based on the proposed criteria. Finally, the WERs and RTFs are examined with each lexicon. In the experiment, 0.72% WER reduction is obtained by introducing the variants pruning criteria. Furthermore, RTF is not deteriorated although the average number of variants is higher than that of compared lexica.

• Korean Linguistics
• /
• v.65
• /
• pp.295-320
• /
• 2014

The idiom is listed in the lexicon, because it's meaning cannot be inferred from it's constituents. And the idiom is a single semantic unit. Thus the idiom is inserted to the syntax in the quality of a word. But the idiom is not always inserted to the syntax as a word. In the process generating the sentence, we can recognize the categorial property of the idiom that it is formally equal to the syntactic phrase. Then each of the constituents of the idiom can be inserted to the syntax. This is why the syntactic operation(as modification, topicalization, relativization, etc) can be applied to the constituent of the idiom. In this respect the idiom is a flexible construction as the listeme of a lexicon. The flexible property of the idiom is related to the dynamicity of a lexicon. The formal or semantic transformation of the idiom is the good example to show the dynamicity of a lexicon.

• MALSORI
• /
• no.64
• /
• pp.137-153
• /
• 2007

The pronunciation lexicon of a continuous speech recognition system should contain enough pronunciation variations to be used for building a search space large enough to contain a correct path, whereas the size of the pronunciation lexicon needs to be constrained for effective decoding and lower perplexities. This paper describes a procedure for selecting pronunciation variations to be included in the lexicon based on the frequencies of the corresponding phonetic rules observed in the training corpus. Likelihood of a phonetic rule's application is estimated using the observation frequency of the rule and is used to control the construction of a pronunciation lexicon. Experiments with various pronunciation lexica show that the proposed method is helpful to improve the speech recognition performance.

• Annual Conference of KIPS
• /
• 2017.04a
• /
• pp.916-919
• /
• 2017

최근 딥러닝의 발달로 인해 Sentiment analysis분야에서도 다양한 기법들이 적용되고 있다. 이미지, 음성인식 분야에서 높은 성능을 보여주었던 Convolutional Neural Networks (CNN)은 최근 자연어처리 분야에서도 활발하게 연구가 진행되고 있으며 Sentiment analysis에도 효과적인 것으로 알려져 있다. 기존의 머신러닝에서는 lexicon을 이용한 기법들이 활발하게 연구되었지만 word embedding이 등장하면서 이러한 시도가 점차 줄어들게 되었다. 그러나 lexicon은 여전히 sentiment analysis에서 유용한 정보를 제공한다. 본 연구에서는 SemEval 2017 Task4에서 제공한 Twitter dataset과 다양한 lexicon corpus를 사용하여 lexicon을 CNN과 결합하였을 때 모델의 성능이 얼마큼 향상되는지에 대하여 연구하였다. 또한 word embedding과 lexicon이 미치는 영향에 대하여 분석하였다. 모델을 평가하는 metric은 positive, negative, neutral 3가지 class에 대한 macroaveraged F1 score를 사용하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.2
• /
• pp.53-60
• /
• 2020

Sentiment analysis is the automated process of understanding attitudes and opinions about a given topic from written or spoken text. One of the sentiment analysis approaches is a dictionary-based approach, in which a sentiment dictionary plays an much important role. In this paper, we propose a method to automatically generate Korean sentiment lexicon from the well-known English sentiment lexicon called VADER (Valence Aware Dictionary and sEntiment Reasoner). The proposed method consists of three steps. The first step is to build a Korean-English bilingual lexicon using a Korean-English parallel corpus. The bilingual lexicon is a set of pairs between VADER sentiment words and Korean morphemes as candidates of Korean sentiment words. The second step is to construct a bilingual words graph using the bilingual lexicon. The third step is to run the label propagation algorithm throughout the bilingual graph. Finally a new Korean sentiment lexicon is generated by repeatedly applying the propagation algorithm until the values of all vertices converge. Empirically, the dictionary-based sentiment classifier using the Korean sentiment lexicon outperforms machine learning-based approaches on the KMU sentiment corpus and the Naver sentiment corpus. In the future, we will apply the proposed approach to generate multilingual sentiment lexica.

• Journal of the Korean School Mathematics Society
• /
• v.24 no.1
• /
• pp.107-126
• /
• 2021

Lexicon is closely related to human thinking. In particular, a classroom lexicon results from objectifying the teaching-learning activity in classrooms, allowing humans to recognize and explore the activities and phenomena in classrooms explicitly. Therefore, using the lexicon and clarifying what the words mean is to enhance the understanding of teaching activities. The International Classroom Lexicon Project investigates and identifies each country's mathematics classroom lexicon, where ten countries participated. The purpose of this current study is to compare the differences in perceptions between teachers and pre-service teachers about the Korean classroom lexicon previously investigated as a part of the international collaborative project. By comparing the responses of 147 teachers and 127 pre-service teachers, the degree of familiarity with pedagogical terms and the frequency of occurrence or usage in classrooms were compared and analyzed to understand the recognition of pre-service teachers' pedagogical terms. Finally, we also discuss reflections on Korean mathematics teaching practices in Korea.

• Annual Conference on Human and Language Technology
• /
• 1993.10a
• /
• pp.371-377
• /
• 1993

본 논문에서는 문자 인식이 끝난 한국어 원문에 대해 한국어 Lexicon에 기반을 둔 후처리의 구현을 보여주는 것을 목적으로 한다. 빈번하게 오인식되는 음절에 대해 이의 옳은 음절을 대응시킨 테이블을 만들어 놓고, 오인식이라고 정의된 음절이 출현했을 때는 이를 원래의 옳은 음절로 대체시킨 어절과 오인식된 음절이 포함된 어절에 대해 한국어 형태소 분석을 행함으로써, 올바른 형태소가 분석될 경우, 이를 옳은 음절로 간주한다. 실험결과 약 90%에서 95%에 달하는 인식율이 이 후처리 방법에 의해서 95%에서 99%로 높아졌다.

• ETRI Journal
• /
• v.35 no.5
• /
• pp.838-848
• /
• 2013

This paper presents a novel approach to automatically generate Korean multiword sentiment expressions by using a seed sentiment lexicon and a large-scale domain-specific corpus. A multiword sentiment expression consists of a seed sentiment word and its contextual words occurring adjacent to the seed word. The multiword sentiment expressions that are the focus of our study have a different polarity from that of the seed sentiment word. The automatically extracted multiword sentiment expressions show that 1) the contextual words should be defined as a part of a multiword sentiment expression in addition to their corresponding seed sentiment word, 2) the identified multiword sentiment expressions contain various indicators for polarity shift that have rarely been recognized before, and 3) the newly recognized shifters contribute to assigning a more accurate polarity value. The empirical result shows that the proposed approach achieves improved performance of the sentiment analysis system that uses an automatically generated lexicon.