• ETRI Journal
• /
• v.43 no.6
• /
• pp.1038-1048
• /
• 2021

We propose an end-to-end neural coreference resolution for the Korean language that uses an attention mechanism to point to the same entity. Because Korean is a head-final language, we focused on a method that uses a pointer network based on the head. The key idea is to consider all nouns in the document as candidates based on the head-final characteristics of the Korean language and learn distributions over the referenced entity positions for each noun. Given the recent success of applications using bidirectional encoder representation from transformer (BERT) in natural language-processing tasks, we employed BERT in the proposed model to create word representations based on contextual information. The experimental results indicated that the proposed model achieved state-of-the-art performance in Korean language coreference resolution.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.182-191
• /
• 2007

This paper gives a thorough investigation into Mandarin sentence-final particles (henceforth SFPs). First I induce core grammatical functions and semantic interpretations of SFPs. Based on Rizzi's (1997) Split CP hypothesis, I make some modifications to accommodate Mandarin SFPs and map them onto separate functional heads within a proper hierarchy. I also examine some empirical evidence of head directionality and tentatively assume Mandarin C is head-initial. To explain the surface head-final order, in light of Chomsky's (2001) Phase Theory and Hsieh's (2005) revised Spell-out hypothesis, I pose a CP complement to Spec movement. Following Moro's (2000) idea, I further claim the motivation behind is to seek for antisymetry.

• Language and Information
• /
• v.18 no.2
• /
• pp.59-79
• /
• 2014

This paper aims at exploring the processing mechanism of filler-gap dependency resolution and feature checking in Korean wh-constructions. Based on their findings on Japanese sentence processing, Aoshima et al. (2004) have argued that the parser posits a gap in the embedded clause in head-final languages, unlike in head-initial languages, where the parser posits a gap in the matrix clause. In order to verify their findings in the Korean context, and to further explore the mechanisms involved in processing Korean wh-constructions, the present study replicated the study done by Aoshima et al., with some modifications of problematic areas in their original design. Sixty-four Korean native speakers were presented Korean sentences containing a wh-phrase in four conditions, with word order and complementizer type as the two main factors. The participants read sentences segment-by-segment, and the reading times at each segment were measured. The reading time analysis showed that there was no such slowdown at the embedded verb in the scrambled conditions as observed in Aoshima et al. Instead, there was a clear indication of the wh-feature checking process in terms of a major slowdown at the relevant region.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• MALSORI
• /
• no.19_20
• /
• pp.58-87
• /
• 1990

According to Government Phonology, at 1 phonological positions save the domain's head must be licensed in order to appear in the syllable structure. A non-nuclear head is licensed by the following nucleus, and the nuclei with phonetic content are licensed through government by the nuclear head of the domain at the level of the nuclear projection. Therefore, in the theory of Government Phonology it is claimed that words always end with a nucleus. With regard to the licensing of empty nuclei, Kaye(1990a) proposes the 'Empty Category Principle' and its sub-theory of 'Projection Government'. Government Phonology claims that a nucleus which dominates a vowel that regularly undergoes elision in certain contexts is underlyingly empty. This underlying empty nucleus is not manifested phonetically when it is properly governed by an unlicensed(i, e, a nucleus filled with a full vowel). It is when proper government fails to apply, that the empty nucleus is phonetically Interpreted. The purpose of this paper is to present a principled account of the process of $[i]{\Leftrightarrow}{\emptyset}$ alternation in Korean. Following Kaye's proposal, we assume that [i] of Korean is underlyingly empty. This position is pronounced as [i] if it is unlicensed, and is not phonetically realized if is licensed. Empty nuclei ape devided into two categories: domain-internal and domain-final. Firstly, we consider the question why Korean has little word ending with [i]. As for this, ECP states that domain-final empty nuclei are not pronounced if the language licenses domain-final empty nuclei. Whether a final empty nucleus may occur in the structure is parametric variation. This property is seen from the fact that words may appear to end in consonants in this language. Since Korean abounds with words ending in a consonant, it licenses domain-final empty nuclei. Therefore, it is quite natural that Korean has little word ending with [i]. Secondly, word-internal empty nuclei of Korean respect proper government and inter-onset government. That is, an empty nucleus in word-internal position will be pronounced with the vowel [i] if either proper government or inter-onset government fail to apply. Inter-onset government refers to the government established between two onsets across an empty nucleus. Thirdly, we consider words ending with [i], which seems to be exceptional to the final licensing. Host of them are. either mono-syllabic verbs(for instance, [s'i-] 'to write') or derived adjectives ending with [p'i] (for instance, [kip'i-] 'be happy'). As for the former, the 'inaccessibility for proper government' is applied because the empty nucleus appears in the first syllable. In latter case, domain-final empty nuclei are pronounced as [i] because of government-licensing. That is, final empty nucleus is pronounced to license the preceding onset dominating negatively charmed segments which empty nucleus of Korean cannot license.

• Annual Conference on Human and Language Technology
• /
• 2004.10d
• /
• pp.259-263
• /
• 2004

본 연구는 머리어-후행언어(head-final language)로 분류되는 한국어의 통사 및 의미 처리 과정의 언어간(cross linguistic) 일반성과 언어내(intra-language) 특이성을 ERP(event- related potentials) 실험결과를 통해 알아보고자 하였다. 한국어 문장처리 과정에서의 통사 및 의미 처리특성은, 우선 이들을 지표하는 각각의 오류문을 통해 P600과 N400 이라는 언어일반의 처리과정을 보이면서도 각 성분의 영역분포는 오류가 출현된 위치에 따라 분기하고 있음을 관찰할 수 있었다. 곧, 문미위치의 술어오류에서 중심-두정 부위의 활성화 우세로 각 오류간 영역분화를 보이는 패턴을 새롭게 확인하였다. 이로써 오류의 유형별 재분류과정으로 드러난 오류출현 위치가 오류의 유형 내에 영향을 끼치는 한 변수가 될 수 있으며. 이는 이들 보어 및 술어를 구성하는 고유의 범주 특성으로 해석할 수 있는 근거가 될 수 있음도 아울러 확인하였다.

• Journal of English Language & Literature
• /
• v.55 no.1
• /
• pp.129-152
• /
• 2009

The paper aims to prove symmetries of the left and right edges of a morphological unit through the analysis of English blends. Blends are the words derived from two existing words by snipping the middle parts out and putting the rest together, such as smog (

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1994.10a
• /
• pp.141-148
• /
• 1994

In order to improve the productivity of cold forging at low production cost, an integrated system's approach is necessary in handling the material preparation and the optimum process design, considering the forming machines, tooling, and operation including quality control. As the first step toward this approach, an expert system for multi-stage cold forging process design for fasteners with various head geometries is developed using Prolog language on IBM 486 PC. For effective representation of the complex part geometries, the system uses the multiple element input, and the forward inference scheme in determination of the initial billet size and intermediate forging steps. In order to determine intermediate steps, the basic empirical rules for extrusion, heading, and trimming were applied. The required forming loads and global strain distributions at each forging step were calculated and displayed on the PC monitor. The designed process sequence drawing can be obtained by AutoCAD. The developed system will be useful in reducing trial and error of design engineers in determining the diameter and height of the initial cylindrical billet from the final product geometry and the intermediate necessary sequences.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.13-18
• /
• 2018

구문 분석은 문장의 구조를 이해하며 의미의 중의성을 해결하는 것이다. 일반적으로 한국어는 어순 배열의 자유도가 높고 문장 성분의 생략이 빈번한 특성이 있기 때문에 의존 구문 분석이 주된 연구 대상이 되어 왔다. 스택-포인터 네트워크 모델은 의존 구문 파서에 맞게 포인터 네트워크 모델을 확장한 것이다. 스택-포인터 네트워크는 각 단어에서 의존소를 찾는 하향식 방식의 모델로 기존 모델의 장점을 유지하면서 각 단계에서 파생된 트리 정보도 사용한다. 본 연구에서는 스택-포인터 네트워크 모델을 한국어에 적용해보고 이와 함께 어절 정보를 반영하는 방법을 제안한다. 모델의 실험 결과는 세종 구문 구조를 중심어 후위(head-final)를 엄격히 준수하여 의존 구문 구조로 변환한 것을 기준으로 UAS 92.65%의 정확도를 얻었다.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.249-258
• /
• 2007

This paper presents an implementation of a gramar of Dynamic Syntax for Japanese. Dynamic Syntax is a grammar formalism which enables a parser to process a sentence in an incremental fashion, establishing the semantic representation. Currently the application of lexical rules and transition rules in Dynamic Syntax is carried out arbitrarily and this leads to inefficient parsing. This paper provides an algorithm of rule application and partitioned parsing state for efficient parsing with special reference to processing Japanese, which is one of head-final languages. At the present stage the parser is still small but can parse scrambled sentences, relative clause constructions, and embedded clauses. The parser is written in Prolog and this paper shows that the parser can process null arguments in a complex sentence in Japanese.