글로버메뉴 바로가기 본문 바로가기 하단메뉴 바로가기

논문검색은 역시 페이퍼서치

국제 워크샵검색

N/A


  • - 주제 : 어문학분야 > 언어학
  • - 성격 : 학술지
  • - 간기: 기타
  • - 국내 등재 : -
  • - 해외 등재 : -
  • - ISSN :
  • - 간행물명 변경 사항 :
논문제목
수록 범위 : 1995권 0호 (1995)

Prototype Theory and Case Assignment

( Yumiko Kinjo ) , ( Kobe University )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 157-162 ( 총 6 pages)
4,500
키워드보기
초록보기
Case assignment is one of the most important issues in theoretical lin-guistics. The goal of this paper is to describe both syntactic and semantic bases for case assignment in terms of PrototY.I.1~theory [1,4}. and to give an explanation for the difference in case assignment between English and Japanese by examining the Instrument Subject construction and deverbal nouns. English allows the structural case assignment under the syntactic prototype, while Japanese does not, because it has a strong requirement for the semantic prototype.

HMM Parameter Learning for Japanese Morphological Analyzer

( Koichi Takeuchi ) , ( Yuji Matsumoto )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 163-172 ( 총 10 pages)
4,500
키워드보기
초록보기
This paper presents a method to apply Hidden Markov Model (HMM) to parameter learning for Japanese morphological analyzer. We especially emphasize how the following two information sources affect the results of the parameter learning: 1) The initial value of parameters, i.e., the initial probabilities and 2) some grammatical constraints that hold in Japanese sen?tences independently of any domain. First and foremost, a simple application of HMM to Japanese corpus does not give a satisfactory results since word boundaries are not clear in Japanese texts because of lack of word sepa?rators. The first results of the experiments show that initial probabilities learned from correct tagged corpus affects greatly to the results and that a small tagged corpus is enough for the initial probabilities. The second result is that the incorporation of simple grammatical constraints works well in the improvements of the results. The final result gives that the total performance of the HMM- based parameter learning achieves almost the same level as the human developed rule-based Japanese morphological analyzer.

Automatic Acquisition of Class-based Rules for Word Alignment

( Sur Jin Ker ) , ( Jason J. S. Chang )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 173-183 ( 총 11 pages)
5,100
키워드보기
초록보기
In this paper, we describe an algorithm for aligning words with their translation in a bilingual corpus. Existing algorithms require enormous bilingual data to train statistical word-to-word translation models. Using word-based approach, frequent words with consistent translation can be aligned at a high precision rate. However, less frequent words or words with diverse translations usually do not have statistically significant evidence for confident alignment. Incomplete or incorrect alignments consequently result. Our algorithm attempts to handle the problem using a hierarchical class-based approximation of translation probabilities. The translation probabilities are estimated using class-based models on 3 levels of specificity. We found that the algorithm can provide translation probability for more word pairs at the cost of slightly lower degree of precision, even when a small corpus was used in training. We have achieved an application rate of 81.8% and precision rate of93.3%. The algOrithm also offer the advantage of producing word-sense disambiguation information.

AUTOMATED ALIGNMENT IN MULTILINGUAL CORPORA

( J. A. Campbell ) , ( Alex Chengyu Fang )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 185-193 ( 총 9 pages)
4,500
키워드보기
초록보기
Experiences in computing alignments at the paragraph and sentence level within a project TRANSLEARN in the European Union``s "LRE" programme of research and development in language engineering are reported. About 98% of the sentences in pairs of corpora in different languages have been aligned correctly by a method that uses dynamic programming on numbers of characters per sentence. This paral-lels the experience of previous researchers for English-French alignment We have used Portuguese and Greek material in addition to these languages. from a set of 49 European Union official documents. It is argued that the key issue of automated alignment is now the automated improvement of the quality of alignment achieved by methods that rely only on character counts. Cues that are helpful to support such an improvement are identified: special words. cognates, syntactic fragments. and a simple measure of seman-tic weight. A short account of their use in experiments is given.

Using Brackets to Improve Search for Statistical Machine Translation

( Dekai Wu ) , ( Chindy Ng )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 195-204 ( 총 10 pages)
4,500
키워드보기
초록보기
We propose a method to improve search time and space complexity in statistical machine translation architectures, by employing linguistic bracketing information on the source language sentence. It is one of the advantages of the probabilistic formulation that competing translations may be compared and ranked by a. principled measure, but at the same time, optimizing likelihoods over the translation spa.ce dictates heavy search costs. To make statistical architectures practical, heuristics to reduce search computation must be incorporated. An experiment applying our method to a prototype Chinese-English translation system demonstrates substantial improvement.

Reference in Dialogues and Shared Belief Revision

( Norihiro Ogata ) , ( Tadayuki Matsuzawa ) , ( Akira Ishikawa ) , ( Hisashi Komatsu )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 205-214 ( 총 10 pages)
4,500
키워드보기
초록보기
We shall show how to treat shared belief revision and reference management in the process of dialogues by distinguishing three types of discourse referents: (standard) discourse referents, shared discourse referents, and the shared belief referent, using an extended version of Discourse Representa?tion Theory, called Hyper-DRS, which can represent shared beliefs semantically in a notation based on hyper-sets (sets in non-well-founded set theory).

Recursion Problems in Concatenation: A Case of Korean Morphology

( Kiyong Lee )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 215-224 ( 총 10 pages)
4,500
키워드보기
초록보기
Without properly constraining recursions in generation, no language system can effectively operate. This is especially so with morphological generation, for each well-formed word must be finite in length and is ac-cepted as such only when it actually occurs in text or ordinary usage. This difficulty is compounded when a language system tries to maintain a single rule of concatenation and apply it repeatedly in order to combine a nominal or verbal stem with a sequence of suffixes in a time-linear man-ner. In an agglutinative language like Korean, however, it can easily be demonstrated how a language system like Malaga, based on time-linear grammars like Hausser``s [1] Left-Associative Grammar, can properly be implemented to constrain undesirable recursive loops in generation. Both nominal and verbal concatenations in Korean are treated in this paper to show how infinite loops can be blocked by imposing appropriate matching conditions on two adjacent input strings to concatenation.

Interpretational Strategies and Semantic Identities

( Ioannis Kanellos ) , ( Victor Hugo Zaldivar Carrillo )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 225-229 ( 총 5 pages)
4,500
키워드보기
초록보기
It is not possible to model semantics of natural language unless one can clearly establish the structure of contextual information and how "context" guides the construction of semantic identities of linguistic units. We claim that this cannot be done unless one can overcome the representational locality imposed by extensional formalisms. In this paper we present a formalism aiming at setting up a non-extensional framework allowing the expression of a notion of context. The very notion of identity is revisited and some forms of non-extensional identity are proposed. In the last section we suggest a representation of metaphor understanding that implements a form of interaction between global contextual information and local semantic identities.

Preferred Clause Structure n Mandarin Spoken and Written Discourse

( Shu Mei Liu )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 231-235 ( 총 5 pages)
4,500
키워드보기
초록보기

A Corpus-Based Study of Adverbial Clauses in Mandarin Chinese Conversations: A Preliminary Analysis

( Yu Fang Wang )
한국언어정보학회|국제 워크샵  1995권 0호, 1995 pp. 237-241 ( 총 5 pages)
4,500
키워드보기
초록보기
In conversation, adverbial clause subordination is most commonly achieved through temporal, conditional, concessive, and causal conjunctions, such as dang (``when``), rnguo(``if), suiran (``although``), yinwei (``because``), etc. in Mandarin Chinese. This study aims at exploring adverbial clauses in spoken Mandarin conversations on the basis of quantitative analysis. There were two-hour conversation database in this research. The adverbial clauses in our database were divided into (a) preposed clauses to their modified material with continuing intonation, (b) postposed clauses to their modified material \-vith continuing intonation, and (c) postposed clauses to their modified material with final intonation (rising question intonation or final falling intonation) After an inspection of our data, we fmd that the temporal, conditional, and concessive clauses favor to occur before their modified material; and the causal ones, after their associated material. Our data show that causal clauses are fundamentally different from temporal, conditional, and concessive ones in their use.
<< 1 2 3 4 >