• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.119-121
• /
• 2016

최근 사람과 컴퓨터가 대화를 하는 채팅시스템 연구가 활발해지고 있다. 컴퓨터가 사람의 말에 적절한 응답을 하기 위해선 그 의미를 분석할 필요가 있다. 발화에 대한 의미 분석의 기본이 되는 연구로 감정분석과 화행분석이 있다. 그러나 이 둘은 서로 밀접한 연관이 있음에도 불구하고 함께 분석하는 연구가 시도 되지 않았다. 본 연구에서는 Long Short-term Memory(LSTM)를 이용하여 대화체 문장의 감정과 화행, 서술자를 동시에 분석하는 통합 대화 분석모델을 제안한다. 사랑 도메인 데이터를 사용한 실험에서 제안 모델은 감정 58.08%, 화행 82.60%, 서술자 62.74%의 정확도(Accuracy)를 보였다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.233-236
• /
• 2020

개체 연결 태스크는 문장 내에 등장하는 멘션(Mention)들을 위키피디아(Wikipedia)와 같은 지식 베이스 상의 실제 개체에 연결하는 태스크이다. 본 논문에서는 각 멘션을 시멘틱(Semantic)으로 분류하여 각 시멘틱별 추가 학습을 진행할 수 있는 Adapter Memory Network 모델을 제안한다. 이는 각 시멘틱 별 학습을 하나의 통합된 과정으로 진행하도록 하는 모델이며, 본 논문에서는 Adapter Memory Network 모델을 통해 기존 개체 연결 태스크에서 높은 성능을 보이는 NIL 멘션 탐지와 개체 연결의 통합 모델의 성능을 향상시켰음을 보인다.

• Informatization Policy
• /
• v.31 no.1
• /
• pp.32-52
• /
• 2024

This study investigates the effectiveness of virtual reality agents as foreign language instructors with focus on the impact of different native language backgrounds and instructional roles. The agents were first distinguished as native or non-native speakers treated as a between-subject factor, and then assigned roles as either teachers or salespersons considered within-subject factors. An immersive virtual environment was developed for this experiment, and a 2×2 mixed factorial design was carried out. In an experimental group of 72 university students, statistically significant interactions were found in learning satisfaction, memory, and recall between the native/non-native status of the agents and their roles. With regard to learning confidence and presence, however, no statistically significant differences were observed in both interaction effects and main effects. Contextual learning in a virtual environment was found to enhance learning effectiveness and satisfaction, with the nativeness and the role of agents influencing learners' memory; thus highlighting the effectiveness of using virtual reality agents in foreign language learning. This suggests that varied approaches can have positive cognitive and emotional impacts on learners, thereby providing valuable theoretical and empirical implications.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.11
• /
• pp.2903-2913
• /
• 1997

This paper describes the design and implementation of the ParaC language that supports parallel programming on the shared memory and distributed memory parallel machine. The ParaC language is designed for the effective use of system resources of scalable parallel systems. The goal is achieved by adding parallel and synchronization constructs for shared address spaces, and remote task constructs for distributed address spaces. This paper also shows the translation method, and we implement the translator and the run-time library for parallel execution of extended constructs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.345-347
• /
• 2023

Rust has gained popularity as a memory safe systems programming language. At the center of its memory safety is a strict memory ownership model with stringent rules enforced by the compiler. This paper aims to shed light on this memory safety model and the role smart pointers play towards its success. We study specific smart pointers, their purposes and contribution to Rust's memory safety. We further explore weaknesses of these smart pointers and their APIs, and provide scenarios under which they may lead to memory vulnerabilities in Rust programs.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.5
• /
• pp.44-51
• /
• 1999

This paper presents a massively parallel computational model for the efficient integration of speech and natural language understanding. The phoneme model is based on continuous Hidden Markov Model with context dependent phonemes, and the language model is based on a knowledge base approach. To construct the knowledge base, we adopt a hierarchically-structured semantic network and a memory-based parsing technique that employs parallel marker-passing as an inference mechanism. Our parallel speech recognition algorithm is implemented in a multi-Transputer system using distributed-memory MIMD multiprocessors. Experimental results show that the parallel speech recognition system performs better in recognition accuracy than a word network-based speech recognition system. The recognition accuracy is further improved by applying code-phoneme statistics. Besides, speedup experiments demonstrate the possibility of constructing a realtime parallel speech recognition system.

• Journal of English Language & Literature
• /
• v.59 no.4
• /
• pp.545-567
• /
• 2013

Keeping in mind the hybridity and plurality of Southern Literature, this paper discusses the traits of Southern literature in Jayne Ann Phillips's first novel, Machine Dream. The novel's frequent use of memory and oral reconstruction of a family history accompanied by the feeling of loss in the process of depicting the South's past typically signifies "The Southern" which reminds us of the works of William Faulkner, Katherine Ann Porter, and Eudora Welty. Nevertheless, Phillips's South is more fragmented and her narrative is more evasive and varied than any of her Southern predecessors. The South of the twentieth century from the period of Depression until 1972 is reconstructed differently depending on memories and desires of the four members of Hampson family in this novel, either as a place of nostalgia or as the place of trauma or as the place to survive only in memory. The oxymoronic title of the novel, "machine dreams" signifies that dream and memory of the South cannot remain independent in its epistemological entity but exist as a mixture of materiality of every day life in the modern South. The hybridity of this dream and of the South is what defines itself as Southern. Yet Phillips retains feeling of loss and lament enough to create a modern Southern novel rooted in Southern Literature. Thus, the title itself works an antinomic signifier of both the presence and absence of the dream of the South and of Southern Literature.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.14 no.4
• /
• pp.391-406
• /
• 2014

The performance of General-Purpose computation on Graphics Processing Units (GPGPU) is heavily dependent on the memory access behavior. This sensitivity is due to a combination of the underlying Massively Parallel Processing (MPP) execution model present on GPUs and the lack of architectural support to handle irregular memory access patterns. Application performance can be significantly improved by applying memory-access-pattern-aware optimizations that can exploit knowledge of the characteristics of each access pattern. In this paper, we present an algorithmic methodology to semi-automatically find the best mapping of memory accesses present in serial loop nest to underlying data-parallel architectures based on a comprehensive static memory access pattern analysis. To that end we present a simple, yet powerful, mathematical model that captures all memory access pattern information present in serial data-parallel loop nests. We then show how this model is used in practice to select the most appropriate memory space for data and to search for an appropriate thread mapping and work group size from a large design space. To evaluate the effectiveness of our methodology, we report on execution speedup using selected benchmark kernels that cover a wide range of memory access patterns commonly found in GPGPU workloads. Our experimental results are reported using the industry standard heterogeneous programming language, OpenCL, targeting the NVIDIA GT200 architecture.

• The Journal of the Korea Contents Association
• /
• v.15 no.4
• /
• pp.545-555
• /
• 2015

We investigated the influence of negative emotion such as state-trait anxiety and depression and working memory (WM) on Foreign Language Vocabulary Learning (FLVL) of South Korean university students. Also, its implications for developing contents for FLVL were discerned. To do so, state-trait anxiety and depression inventories as well as four kinds of WM test were performed for 132 undergraduate students. Participants also had two semantic learning sessions for Swahili words. The mean scores of negative emotions were normal level. The results of structural equation modeling (SEM) showed that there was no effect of negative emotion on FLVL, while direct effects of the negative emotion on WM and the WM on FLVL were significant. Such results suggested that FLVL would be weakened, with the result that WM had been impaired by negative emotions. These outcomes suggested that when developing FLVL content for university students, it is necessary to consider the negative emotions of foreign language learners and to develop the contents for FLVL in the light of WM load.