• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.24-29
• /
• 2022

Semantic role labeling task used in various natural language processing fields, such as information extraction and question answering systems, is the task of identifying the arugments for a given sentence and predicate. Predicate used as semantic role labeling input are extracted using lexical analysis results such as POS-tagging, but the problem is that predicate can't extract all linguistic patterns because predicate in korean language has various patterns, depending on the meaning of sentence. In this paper, we propose a korean predicate recognition method using neural network model with pre-trained embedding models and lexical features. The experiments compare the performance on the hyper parameters of models and with or without the use of embedding models and lexical features. As a result, we confirm that the performance of the proposed neural network model was 92.63%.

• Journal of the Korean earth science society
• /
• v.31 no.7
• /
• pp.785-797
• /
• 2010

This study identified the linguistic features of Earth science treatises through the analysis of the register. Data included three Korean treatises that were in geology, atmospheric science, and oceanography. The register of Earth science treatise was as follows: First, there were semantic, referential connections between Themes and Rhemes, that the messages and main points of the texts were expressed coherently and cohesively. Second, some predicates were used which were related to deductive inference, abductive inferences, or causal relation according to the genre elements of each text. The logical relations were not represented by the conjunctions but by the types of predicates. Third, most texts in the treatises showed interpersonally weak relationship using mental predicates related to possibilities, which meant scientists expressed indirectly their interpretation, explanation, or arguments. From these results, we argued that some activities of unpacking the language of science be included in science curriculum in order to improve students' literacy of science texts and understanding scientists' knowledge construction.

• 한국노년학
• /
• v.32 no.3
• /
• pp.747-758
• /
• 2012

Detecting probable Alzheimer's disease (AD) at an early stage is crucial in slowing the progression of the disease and initiating drug therapy for more effective symptom management. Therefore, this study aimed to identify linguistic features that allow us to distinguish between patients with AD and normal controls. This paper reports on characteristics of spontaneous speech in subjects in three stages of AD (questionable, mild, moderate) compared with education- and age-matched normal controls. Four components of speech were measured in Korean native speakers with AD and normal aging: speech tempo, hesitation (measured in seconds), rate of articulation errors, and rate of grammatical errors. The results revealed significant differences in most of these speech components among the four groups, including significant differences between normal controls and the questionable AD group in the areas of speech tempo and rate of grammatical errors. Phonological? articulatory ability was preserved in questionable AD, and grammatical ability was preserved in questionable and mild AD. Subjects with moderate AD were severely impaired in grammatical ability. Prospective assessments of spontaneous speech skills using a dialogue and picture-description task are useful in detecting the subtle, spontaneous speech impairments that AD causes even in its early stage.

• The Journal of the Korea Contents Association
• /
• v.22 no.10
• /
• pp.426-436
• /
• 2022

This study aimed to explore the role of models and reformulations as feedback to English writing in L2 learners' noticing and their writing. 92 participants were placed into three groups; a models group (MG), a reformulations group (RG), a control group (CG), involved in a three-stage writing task. In stage 1, they were asked to perform a 1st draft of writing, while taking notes on the problems they experienced. In stage 2, the MG was asked to compare their writing with a model text and the RG with a reformulated version of it. They were instructed to write down whatever they noticed in their comparison. The CG was asked to just read their writing. In stage 3, all the participants attempted subsequent revisions. The results indicated that all the participants noticed problematic linguistic features the most in a lexical category, and models and reformulations led to higher rate of noticing the problematic linguistic features reported in stage 1 and contributed to subsequent revisions. It was also revealed that the MG and RG significantly improved with their writings of MG and RG on the post-writing test. The findings imply that models and reformulations result in better performance in L2 writing and should be promoted in an English writing class.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2001.06a
• /
• pp.199-225
• /
• 2001

The main goal of this paper is to investigate and compare English, German and Korean non-head-bound-intensifiers such as English ‘x-self’, German ‘selbst’, and Korean ‘susulo, casin’. That is, this paper is mainly concerned with the semantic domain where the respective contributions of the expressions in question overlap. The phenomenon under discussion with the label “intensifiers” is regarded as universal, which provides the ground of the comparative/contrastive or semi-cross-linguistic study of this paper. Not only the semantic concept of intensification by these expressions but also the combination of grammatical features or syntactic behaviours thereof seem to have highly invariant common denominators among the wide varieties of languages, even if they come from apparently different language families. In comparing English, German and Korean intensifiers, this paper is interested in the more general features of the expressions in question rather than some language-specific idiocyncracies. Intensifiers work similarly not only in English and German, but also in Korean. Each of three languages under investigation provides some sort of a safegard against confusing instances and misleading judgements on the issues under discussion. Morphologically, however, English expressions in question agree with their rele-vant NP in number, gender and person. Whereas German and Korean counterparts do not have such specific morphological properties. Intensifiers in their non-head-bound-use are subject-oriented, just as in their head-bound use. Non-head-bound-intensifiers differ from head-bound-intensifiers mostly in their syntactic behaviours or distributional properties, whereas they share the semantic domain “intensification” regarding relevant subject-NP. They introduce an ordering and distinguish center and periphery, and ‘self-involvement (directness of involvement)’seems a additional possible characterisation of the relevant dimension of these intensifiers in common. An assertion of identity also can be reg

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.306-312
• /
• 2008

In a goal-oriented dialogue, speaker's intention can be approximated by a semantic structure that consists of a pair of a speech act and a concept sequence. Therefore, it is very important to correctly identify the semantic structure of an utterance for implementing an intelligent dialogue system. In this paper, we propose a model to efficiently analyze the semantic structures based on an active teaming method. To reduce the burdens of high-level linguistic analysis, the proposed model only uses morphological features and previous semantic structures as input features. To improve the precisions of semantic structure analysis, the proposed model adopts CRFs(Conditional Random Fields), which show high performances in natural language processing, as an underlying statistical model. In the experiments in a schedule arrangement domain, we found that the proposed model shows similar performances(92.4% in speech act analysis and 89.8% in concept sequence analysis) to the previous models although it uses about a third of training data.