• Korean Journal of Cognitive Science
• /
• v.23 no.2
• /
• pp.249-267
• /
• 2012

Individual differences in working memory predict qualitative differences in language processing. High span comprehenders are better able to integrate probabilistic information such as plausibility and animacy, the use of which requires the computation of real world knowledge in syntactic parsing (e.g.,[1]). However, it is unclear whether similar individual differences exist in the use of informative prosodic cues. This study examines whether working memory modulates the use of prosodic boundary information in attachment ambiguity resolution. Prosodic boundaries were manipulated in globally ambiguous relative clause sentences. The results show that high span listeners are more likely to be sensitive to the distinction between different types of prosodic boundaries than low span listeners. The findings suggest that like high-level constraints, the use of low-level prosodic information is resource demanding.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.4
• /
• pp.40-46
• /
• 1999

This paper introduce a Koran-Japanese machine translation system which is a module in the spoken language interpreting system It is implemented based on the TDMT(Transfre Driven Machine Translation). We define a new unit of translation so called TOKEN. The TOKEN-based translation method resolves nonstructural feature in Korean sentences and increases the quaity of translating results. In our system, we get rid of useless effort for traditional parsing by performing semi-parsing. The semi-parser makes the dependency tree which has minimum information needed generating module. We constructed the generation dictionaries by using the corpus obtained from ETRI spoken language database. Our system was tested with 600 utterances which is collected from travel planning domain The success-ratio of our system is 87% on restricted testing environment and 71% on unrestricted testing environment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.592-596
• /
• 2002

Can speak that DTD is meta data that define meaning of expressed data on XML document. Therefore, In case DTD information is damaged this information to base security of XML document dangerous. Not that attach digital signature on XML document at send-receive process of XML document in this research, proposed method to attach digital signature to DTD. As reading DTD file to end first, do parsing, and store abstracted element or attribute entitys in hash table. Read hash table and achieve message digest if parsing is ended. Compose and create digital signature with individual key after achievement. When sign digital, problem that create entirely other digest cost because do not examine about order that change at message digest process is happened. This solved by method to create DTD's digital signature using DOM that can embody tree structure for standard structure and document.

• Journal of Korea Multimedia Society
• /
• v.16 no.3
• /
• pp.366-374
• /
• 2013

One of the most important problems in syntactic analysis is syntactic ambiguities. This paper proposes a parsing system and this system can reduce syntactic ambiguities by using segmentation method and argument information method. The proposed system uses morphemes for the input of syntax analysis system, and syntactic analysis system generates all possible parse trees from the given morphemes. Therefore, this system generates many syntactic ambiguity problems. We use three methods to solve these problems. First is disambiguation method in morphological analysis, second is segmentation method in syntactic analysis processing, and the last method is using argument information. Using these three methods, we can reduce many ambiguities in Korean syntactic analysis. In our experiment, our approach decreases about 53% of syntactic ambiguities.

• Journal of KIISE:Software and Applications
• /
• v.32 no.9
• /
• pp.936-947
• /
• 2005

In dependency parsing of long sentences with fewer subjects than predicates, it is difficult to recognize which predicate governs which subject. To handle such syntactic ambiguity between subjects and predicates, this paper proposes an 'S-clause' segmentation method, where an S(ubject)-clause is defined as a group of words containing several predicates and their common subject. We propose an automatic S -clause segmentation method using decision trees. The S-clause information was shown to be very effective in analyzing long sentences, with an improved parsing performance of 5 percent. In addition, the performance in detecting the governor of subjects was improved by $32\%$.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2718-2731
• /
• 2023

This paper presents a method of using syntax and shallow semantic analysis for Vietnamese question generation (QG). Specifically, our proposed technique concentrates on investigating both the syntactic and shallow semantic structure of each sentence. The main goal of our method is to generate questions from a single sentence. These generated questions are known as factoid questions which require short, fact-based answers. In general, syntax-based analysis is one of the most popular approaches within the QG field, but it requires linguistic expert knowledge as well as a deep understanding of syntax rules in the Vietnamese language. It is thus considered a high-cost and inefficient solution due to the requirement of significant human effort to achieve qualified syntax rules. To deal with this problem, we collected the syntax rules in Vietnamese from a Vietnamese language textbook. Moreover, we also used different natural language processing (NLP) techniques to analyze Vietnamese shallow syntax and semantics for the QG task. These techniques include: sentence segmentation, word segmentation, part of speech, chunking, dependency parsing, and named entity recognition. We used human evaluation to assess the credibility of our model, which means we manually generated questions from the corpus, and then compared them with the generated questions. The empirical evidence demonstrates that our proposed technique has significant performance, in which the generated questions are very similar to those which are created by humans.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.612-615
• /
• 1988

This paper proposes a method for analyzing the Korean inflected word in machine translation system. We define the processing rules which are useful of analyzing an irregular conjugation, pesent an parsing algorithm of noun and specifed verb and reduce the space of dictionary by the algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10a
• /
• pp.747-749
• /
• 1998

본 논문에서는 음성과 자연언어의 통합처리를 위한 효과적인 병렬 계산 모델을 제안한다. 음소모델은 continuous HMM에 기반을 둔 문맥종속형 음소를 사용하며, 언어모델은 knowledge-based approach를 사용한다. 또한 계층구조의 지식베이스상에서 다수의 가설을 처리하기 위해 memory-based parsing기술을 사용하였다. 본 연구의 병렬 음성인식 알고리즘은 분산메모리 MIMD 구조의 다중 Transputer 시스템을 이용하여 구현되었다. 실험을 통하여 음성인식 과정에서 발생하는 speech-specific problem의 해를 제공하고 음성인식 시스템의 병렬화를 통하여 실시간 음성인식의 가능성을 보여준다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.507-509
• /
• 2003

본 논문에서 제안하는 영어 Parser는 Bottom-Up Best-First Chart Parser를 기반으로 영어 구문 분석과 동시에 영$\longrightarrow$한 구조변환을 수행한다. 따라서, 영어 입력문에 대한 파서의 결과는 한국어 구운 Tree가 된다. 구문 분석과 변환을 동시에 수행하므로, 번역 과정을 단순화하고 번역지식 관리가 용이하여 번역기의 튜닝이 용이하다. 구현된 파서는 대규모 문법 규칙에 대응하기가 용이하고. 새로운 규칙의 추가가 용이하여 번역기의 점진적인 성능 향상이 가능하다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.419-421
• /
• 2003

본 논문에서는 진화 연산 기법을 이용한 자연어 구운 분석 기법을 제시한다 기존의 확률 문맥 무관문법(PCFG)에 관한 연구는 차트 파싱 방법을 구문 분석을 위한 기법으로 가정하고 있다. 하지만, 차트 파싱은 문장의 길이가 늘어날수록 복잡도가 크게 증가하는 문제를 안고 있다. 따라서, 차트 파서의 대안으로서 진화 연산 기법을 사용하여 이 문제를 해결하였다. 진화 연산의 적합도 함수로는 생성된 파스트리의 확률을 사용하였다. 작은 규모의 자연어 문제에 적용한 결과, 진화 연산이 파싱 문제를 성공적으로 해결할 수 있음을 확인할 수 있었다.