이근배 교수

This paper presents the automatic construction of a Korean WordNet from pre-existing lexical resources. A set of automatic WSD techniques is described for linking Korean words collected from a bilingual MRD to English WordNet synsets. We will show how individual linking provided by each WSD method is then combined to produce a Korean WordNet for nouns.

This paper proposes a combination of convolutional neural network and auto-encoder (CAE) for unsupervised anomaly detection of industrial gas turbines. Autonomous monitoring systems protect the gas turbines, with the settings unchanged in their lifetime. Those systems can not detect any abnormal operation patterns which potentially risk the equipment after long-term exposure. Recently, machine learning and deep learning models are applied for industries to detect those anomalies under the nomina

Most of errors in Korean morphological analysis and POS (Part-of-Speech) tagging are caused by unknown morphemes. This paper presents a generalized unknown morpheme handling method with POSTAG (POStech TAGger) which is a statistical/rule based hybrid POS tagging system. The generalized unknown morpheme guessing is based on a combination of a morpheme pattern dictionary which encodes general lexical patterns of Korean morphemes with a posteriori syllable tri-gram estimation. The syllable tri-gram

This paper describes an approach to identifying the syntactic role of an antecedent in a Korean relative clause, which is essential to structural disambiguation and semantic analysis. In a learning phase, linguistic knowledge such as conceptual co-occurrence patterns and syntactic role distribution of antecedents is extracted from a large-scale corpus. Then, in an application phase, the extracted knowledge is applied in determining the correct syntactic role of an antecedent in relative clauses.

In this paper, we present a new phrase break prediction architecture that integrates probabilistic approach with decision-tree based error correction. The probabilistic method alone usually suffers from performance degradation due to inherent data sparseness problems and it only covers a limited range of contextual information. Moreover, the module can not utilize the selective morpheme tag and relative distance to the other phrase breaks. The decision-tree based error correction was tightly int

In this paper, we present a corpusbased learning method that can index diverse types of compound nouns using rules automatically extracted from a large tagged corpus. We develop an efficient way of extracting the compound noun indexing rules automatically and perform extensive experiments to evaluate our indexing rules. The automatic learning method shows about the same performance compared with the manual linguistic approach but is more portable and requires no human efforts. We also evaluate t

음성 언어 이해는 자연어 음성으로부터 컴퓨터가 처리할 수 있는 형태의 의미를 저장하는 의미 구조를 추출하는 문제를 다룬다. 대부분의 음성 언어 이해 시스템들은 화행 분석과 개체명 분석을 구분하여 처리하고 있다. 기존 연구에서는 이러한 두 가지 문제를 독립적이거나 순차적인 방식으로 처리하고 있다. 하지만 순차적 시스템에서는 화행과 개체명이 한 방향으로만 영향을 주게 되는 단점이 존재한다. 본 논문에서는 화행과 개체명을 동시에 처리하기 위해 Triangular-chain CRF라는 새로운 결합 음성 언어 이해 모델을 제안한다. 음성 대화 데이터를 이용한 실험을 통해 제안하는 결합 모델이 독립 및 순차적 방법과 비교하여 성능이 향상됨을 제시한다.

논문에서는 띄어쓰기 오류와 철자 오류를 동시에 교정 가능한 전처리기를 제안한다. 제시된 알고리즘은 기존의 전처리기 알고리즘이 각 오류를 따로 해결하는 데에서 오는 한계를 극복하고, 기존의 noisy-channel model을 확장하여 대화체의 띄어쓰기 오류와 철자 오류를 동시에 효과적으로 교정할 수 있다. N-gram과 자소변환확률 등의 통계적 방법과 어절변환패턴 사전을 이용하여 최대한 사전을 적게 이용하면서도 효과적으로 교정 후보들을 생성할 수 있다. 실험을 통해 현재 단계에서는 만족할 만한 성능을 얻지는 못하였지만 오류 분석을 통하여 이와 같은 방법론이 실제로 효용성이 있음을 알 수 있었고 앞으로 더 많은 개선을 통해 일상적인 대화체 문장에 대해서 효과적인 전처리기로서 기능할 수 있을 것으로 기대된다.

In this paper, we propose a new language model, namely, a dependency structure language model, for information retrieval to compensate for the weaknesses of unigram and bigram language models. The dependency structure language model is based on the first-order dependency model and the dependency parse tree generated by a linguistic parser. So, long-distance dependencies can be naturally captured by the dependency structure language model. We carried out extensive experiments to verify the propos

The Korean Combinatory Categorial Grammar (KCCG) formalism can uniformly handle word order variation among arguments and adjuncts within a clause as well as in complex clauses and across clause boundaries, i.e., long distance scrambling. In this paper, incremental parsing technique of a morpheme graph is developed using the KCCG. We present techniques for choosing the most plausible parse tree using lexical information such as category merge probability, head-head co-occurrence heuristic, and th

Both statistical and rule-based approaches to part-of-speech (POS) disambiguation have their own advantages and limitations. Especially for Korean, the narrow windows provided by hidden markov model (HMM) cannot cover the necessary lexical and long-distance dependencies for POS disambiguation. On the other hand, the rule-based approaches are not accurate and flexible to new tag-sets and languages. In this regard, the statistical/rule-based hybrid method that can take advantages of both approache