• Title/Summary/Keyword: Pivot language

Search Result 18, Processing Time 0.022 seconds

Research about SMT Performance Improvement Through Automatic Corpus Expansion (말뭉치 자동 확장을 통한 SMT 성능 향상에 대한 연구)

  • Choi, Gyu-Hyun;Shin, Jong-Hun;Kim, Young-Kil
    • 한국어정보학회:학술대회논문집
    • /
    • 2016.10a
    • /
    • pp.296-299
    • /
    • 2016
  • 현재 자동번역에는 통계적 방법에 속하는 통계기반 자동번역 시스템(SMT)이 많이 사용되고 있지만, 학습 데이터로 사용되는 대용량의 병렬 말뭉치를 수동으로 구축하는데 어려움이 있다. 본 연구의 목적은 통계기반 자동번역의 성능을 향상시키기 위해 기존 다른 언어쌍의 말뭉치와 SMT 자동번역 기술을 이용하여 대상이 되는 언어쌍의 SMT 병렬 말뭉치를 자동으로 확장하는 방법을 제안한다. 제안 방법은 서로 다른언어 B와 C의 병렬 말뭉치를 얻기 위해, A와 B의 SMT 자동번역 시스템을 구축하고 기존의 A-C 말뭉치의 A를 SMT를 통해 B로 번역하여 B와 C의 말뭉치를 자동으로 확장한다. 실험을 통해 확장한 병렬 말뭉치가 통계기반 자동번역 시스템의 성능을 향상시킬 수 있음을 확인한다.

  • PDF

Pivot-based Bilingual Lexicon Extraction Using Word2Vec and CCA (중간언어 기반의 Word2Vec와 CCA를 이용한 이중언어 사전 추출)

  • Kim, Jeong-Tae;Kim, Chang-Hyun;Cheon, Min-Ah;Kim, Jae-Hoon;Kim, Jae-Hwan
    • 한국어정보학회:학술대회논문집
    • /
    • 2016.10a
    • /
    • pp.307-309
    • /
    • 2016
  • 이중언어 사전은 자연어처리 분야에서 매우 유용한 자원으로 사용되고 있다. 그러나 초기사전이나 병렬말뭉치 등 자원이 부족한 언어 쌍에 대해서 이중언어 사전을 추출하는 것은 쉽지 않다. 이러한 문제를 해결하기 위해 본 논문에서는 중간 언어 기반으로 Word2Vec와 CCA를 이용하여 이중언어 사전을 추출하는 방법을 제안한다. 본 논문에서 제안하는 방법의 성능을 평가하기 위해서 중간언어로 영어를 사용하여 스페인어-한국어에 대한 이중언어 사전을 추출하는 실험을 하였다. 무작위로 뽑은 200개의 단어에 대한 번역 정확도를 구하였다. 그 결과 최상위에서 37.5%, 상위 10위에서 63%, 그리고 상위 20위에서는 69.5%의 정확도를 얻을 수 있었다.

  • PDF

Style Selection for Korean Generation under the Pivot MT System (피봇 기계번역시스템에서의 한국어생성을 위한 문제선정)

  • 이종혁
    • Korean Journal of Cognitive Science
    • /
    • v.1 no.2
    • /
    • pp.279-291
    • /
    • 1989
  • Major difficulties in the style selection,which guarantees the synthesis of good-styled natural expressions under the PIOVT MT system, are an absence of surface-level extra-information in the languageinde-pendent intermediate representation and the language-specific style of expressions due to cultural differences.This paper describes an attempt on the style selection with capabilities of guaranteeing more natural Korean expressions,which includes pragmatic and stylistic decision on target voice genertaion under heavy passive constraints,stylistic changes of sentence-structures,and meaning-supplementation of function words with content words.

Bilingual Multiword Expression Alignment by Constituent-Based Similarity Score

  • Seo, Hyeong-Won;Kwon, Hongseok;Cheon, Min-Ah;Kim, Jae-Hoon
    • Journal of Information Processing Systems
    • /
    • v.12 no.3
    • /
    • pp.455-467
    • /
    • 2016
  • This paper presents the constituent-based approach for aligning bilingual multiword expressions, such as noun phrases, by considering the relationship not only between source expressions and their target translation equivalents but also between the expressions and constituents of the target equivalents. We only considered the compositional preferences of multiword expressions and not their idiomatic usages because our multiword identification method focuses on their collocational or compositional preferences. In our experimental results, the constituent-based approach showed much better performances than the general method for extracting bilingual multiword expressions. For our future work, we will examine the scoring method of the constituent-based approach in regards to having the best performance. Moreover, we will extend target entries in the evaluation dictionaries by considering their synonyms.

Automatic bilingual lexicon construction via bilingual parallel corpus and pivot language (이국어 병렬말뭉치와 중간언어를 활용한 이국어 사전 자동구축)

  • Seo, Hyeong-Won;Kwon, Hong-Seok;Kim, Jae-Hoon
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2013.05a
    • /
    • pp.307-310
    • /
    • 2013
  • 본 논문은 한국어-스페인어와 한국어-불어 간의 양방향 이국어 사전(Bi-directional bilingual lexicon)을 자동으로 구축하기 위한 새로운 방법을 제안한다. 일반적으로 한국어와 스페인어/불어 간의 병렬 말뭉치를 직접적으로 구축하기에는 어려움에 따르기 때문에, 영어를 중심언어로 하는 영어(EN)-한국어(KR)/스페인어(ES)/불어(FR) 병렬 말뭉치를 이용하여 문맥 벡터를 만들고 그들 간의 유사도를 계산하는 변형된 문맥 벡터 방법을 제안한다. 영어는 다른 언어와의 이국어 병렬 말뭉치가 비교적 많이 공개되어 있기 때문에 이 방법을 이용하면 비교적 쉽게 KR-ES와 KR-FR 양방향 이국어 사전을 구축할 수 있다. 본 논문에서 제안한 방법으로 실험해본 결과 최고 85%(ES${\rightarrow}$KR)의 정확도를 얻을 수 있었다.

Fasting of the Mind and Quieting of the Mind: A Comparative Analysis of Apophatic Tendencies in Zhuangzi and Cataphatic Tendencies in Daesoon Thought

  • ZHANG Rongkun;Jason GREENBERGER
    • Journal of Daesoon Thought and the Religions of East Asia
    • /
    • v.2 no.2
    • /
    • pp.33-50
    • /
    • 2023
  • 'Fasting of the Mind (心齋, ch. xīn zhāi)' is arguably the most important concept within the practical approach to the spiritual cultivation formulated by the Daoist philosopher, Zhuangzi (莊子). Most scholars have interpreted 'Fasting of the Mind' as an apophatic practice centered around the aim of the 'Dissolution of the Self (喪我, ch. sàng wŎ).' The Korean new religious movement, Daesoon Jinrihoe (大巡眞理會), can be shown to instead consistently utilize cataphatic descriptions of spiritual cultivation based on the 'quieting of the mind (安心, kr. anshim)' and 'quieting of the body (安身, kr. anshin)' with the highest attainable state referred to as the 'Perfected State of Unification with the Dao (道通眞境, kr. Dotong-jingyeong).' While the language used by Zhuangzi and Daesoon Jinrihoe appears quite different on a superficial level, a deeper examination shows that these rhetorical framings are likely negativistic and positivistic descriptions of the same, or at least reasonably similar, phenomena. Zhuangzi, who focused primarily on the body, mind, and internal energy, cautioned practitioners that 'mere listening stops with the ears (聽止於耳, ch. tīng zhǐ yú ěr)' and 'mere recognition stops with the mind (心止於符, ch. xīn zhǐ yú fú).' He therefore encouraged cultivators of the Dao to 'listen with the spirit (聽之以氣 ch. tīng zhī yǐ qì).' The main scripture of Daesoon Jinrihoe states that "The mind is a pivot, gate, and gateway for gods; They, who turn the pivot, open, and close the gate, and go back and forth through the gateway, can be either good or evil (心也者, 鬼神之樞機也, 門戶也,道路也)," and the Supreme God of the Ninth Heaven (九天上帝, kr. Gucheon Sangje) even promises to visit anyone who possesses a 'singularly-focused mind (一心, kr. il-shim).' In both these approaches, there is a sense of what must be kept out of the mind (e.g., external disturbances, strong emotions, malevolent entities) and what the mind should connect with to attain spiritual progress (e.g., spirit, singular focus, the Supreme God). The observations above serve as the main basis for a comparison between the apophatic descriptions of cultivation found in Zhuangzi and their cataphatic counterparts in Daesoon Thought. However, the culmination of this nuanced comparative exploration reveals that while the leanings of Zhuangzi and Daesoon Thought generally hold true, ultimately, both systems of cultivation transcend the categories of apophatic and cataphatic.

The Acquisition of Negatives in Five Korean Children (한국 아동의 부정사 획득)

  • Yi, Soon Hyung
    • Korean Journal of Child Studies
    • /
    • v.6 no.1
    • /
    • pp.17-40
    • /
    • 1985
  • This study investigated Korean children's early acquisition of negatives and focused on four research questions: 1) processing of negative variations; 2) the nature of negatives when negatives are completely acquired in Korean (in which meaning and form are matched in one to one mapping); 3) the validity of Bellugi's negative acquisition model in Korean; and 4) the cause of child's erroneous sentence production: limited ability or regularity in children's cognition. The language data of the five subjects (age span; 1.1 - 3.11) were collected by their parents in the natural setting of the home. The results showed that 1) the pivot form, was processed in many ways from a simple to a complicated form, such as <(X+X')+N> <(x+x')+N,Y> <(x+x') N,(y+y')>. It appeared that the children used a simple negative format to reach a one-step advanced negative format. 2) Korean negatives are divided into range of negation in the negative sentence (part or whole), strength of negation (absolute or general), functions of meaning (negation, absences, refusal, prohibition, impossibility). All five children acquired negative sentences in all functions and the complete range after 3 years of age. 3) In spite of the differences in age level, Bellugi's four stage model was in evidence; that is, Korean children's negative acquisition was almost identical with Bellugi's tour stage model in deep structure. 4) Analyses of children's error sentences showed that the sentences with errors were made not because of the children's limitation in cognitive ability but because of the strict application of regularity of rules from the original grammars. Consequently, the children produced negative sentences using two rules: the rule of additive complexity (from simple to complex) and the rule of division (from one to several).

  • PDF

A Symbolic Characteristic of Mimetic Words in Published Cartoon: Focusing on Works of Heo, Young Man (허영만의 작품에서 나타난 효과태의 상징어적 특징과 활용)

  • O, Yul Seok;Yoon, Ki Heon
    • Cartoon and Animation Studies
    • /
    • s.30
    • /
    • pp.169-199
    • /
    • 2013
  • In various directions of cartoon, vertical stroll direction is opposite to the page direction of existing published cartoon with the popularity of webtoon and established new genre. Lots of studies on published cartoon focus on the cut direction by page, but webtoon doesn't have any concept of page. The pivot of cartoon oriented people is changed from paper to computer monitor as times go by, characteristics of media are changed and media is gradually diversified. Like the strengthening of mobile caused by smart phone's popularity, tablet PC's propagation in public education, etc. cartoon is included to the environment of media which is rapidly changed. In this situation, one of cartoon's unchanged important identities can be the direction made by harmony between picture and text. This thesis analyzed symbolic characteristics and effective value of hyogwatae, mimetic words of cartoon, focusing on works of Heo, Young Man. Hyogwatae just delivers not only sound but also shape, feeling, status, etc. and has significant characteristics by invoking the imaginary structure of literature. Strengths of modern Korean, various linguistic expressions and syllabic systems, let people feel minute feeling of language and difference of emotion and remember the memory through the direct and indirect experiences, so it makes it nuance. Because of the characteristics, representative works of Heo, Young Man have commercialization and writer characteristics, have communicated with people for a long time and have plentiful knowledge of Korean cartoon. The characteristics of hyogwatae in Heo, Young Man's cartoon make a lot of effects for the expression and delivery of cartoon more than the general expectation. When conducting the study focusing on the symbolic process of language, uncertainty and vague standard of judgement caused by the wide factors of study on the direction of general cartoon could be endured. And, through the Heo, Young Man's deep analysis on hyogwatae's direction, readers enjoy the process while inferring actually and intellectually between pictures and sentences. In the process, the equipment stimulating imagination more than pictures, effects and dialogues is hyogwatae. It's reader's equipment of active participation and its strength is symbolic structure.