• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.4
• /
• pp.306-311
• /
• 2020

This paper deals with how to improve the performance of Python language with various libraries when developing a model using big data. The Python language uses the Pandas library for processing spreadsheet-format data such as Excel. In processing data, Python operates on an in-memory basis. There is no performance issue when processing small scale of data. However, performance issues occur when processing large scale of data. Therefore, this paper introduces a method for distributed processing of execution tasks in a single cluster and multiple clusters by using a Dask library that can be used with Pandas when processing data. The experiment compares the speed of processing a simple exponential model using only Pandas on the same specification hardware and the speed of processing using a dask together. This paper presents a method to develop a model by distributing a large scale of data by CPU cores in terms of performance while maintaining that python's advantage of using various libraries is easy.

• MALSORI
• /
• no.51
• /
• pp.99-115
• /
• 2004

In this parer, we propose LM adaptation for broadcast news recognition. We collect information of recent articles from the internet on real time, make a recent small size LM, and then interpolate recent LM with a existing LM composed of existing large broadcast news corpus. We performed interpolation experiments to get the best type of articles from recent corpus because collected recent corpus is composed of articles which are related with test set, and which are unrelated. When we made an adapted LM using recent LM with similar articles to test set through Tf-Idf method and existing LM, we got the best result that ERR of pseudo-morpheme based recognition performance has 17.2 % improvement and the number of OOV has reduction from 70 to 27.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.11a
• /
• pp.40-41
• /
• 2019

The purpose of this study is to analyze the vocabulary related to safety accidents based on the reports recorded on the violation of safety rules at the construction sites. We used Word2Vec and Topic Model as natural language processing techniques to analyze the safety accidents presented in the reports of the large enterprise. The words that appeared based on the occupational accident types such as the fall, falling objects, and others were derived and visualized. We derive the frequency and similarity of the words and topics of the accident that occur at the construction site. In future studies, we will be able to proceed with the generation of texts from pictures based on images and this reports.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.327-329
• /
• 2007

This paper presents a FSN-based LVCSR system and it's application to the speech TV program guide. Unlike the most popular statistical language model-based system, we used FSN grammar based on the graph theory-based FSN optimization algorithm and knowledge-based advanced word boundary modeling. For the memory and latency efficiency, we implemented the dynamic pruning scheduling based on the histogram of active words and their likelihood distribution. We achieved a 10.7% word accuracy improvement with 57.3% speedup.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.419-422
• /
• 2021

본 논문은 한국어와 영어 코퍼스 93GB를 활용하여 구축한 대형 사전학습기반 언어모델인 KE-T5를 소개한다. KE-T5는 한국어와 영어 어휘 64,000개를 포함하는 대규모의 언어모델로 다양한 한국어처리와 한국어와 영어를 모두 포함하는 번역 등의 복합언어 태스크에서도 높은 성능을 기대할 수 있다. KE-T5의 활용은 대규모의 언어모델을 기반으로 영어 수준의 복잡한 언어처리 태스크에 대한 연구들을 본격적으로 시작할 수 있는 기반을 마련하였다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.61-65
• /
• 2023

최근, 대부분의 태스크가 초거대 언어 모델로 통합되고 있을 정도로 많은 관심 및 연구되고 있다. 초거대 언어 모델을 효과적으로 활용하기 위해서는 모델의 능력에 대한 분석이 선행되어야 하나, 한국어에 대한 분석 및 탐색은 상대적으로 부족하다. 본 논문에서는 한국어 맞춤법 교정 태스크를 통해 초거대 언어 모델의 능력을 탐색한다. 맞춤법 교정 태스크는 문장의 구조 및 문법을 이해하는 능력이 필요하며, 사용자의 만족도에 영향을 미칠 수 있는 중요한 태스크이다. 우리는 맞춤법 세부 유형에 따른 ChatGPT의 제로샷 및 퓨샷성능을 평가하여 초거대 언어 모델의 성능 분석을 수행한다. 실험 결과 제로샷의 경우 문장부호 오류의 성능이 가장 우수했으며, 수사 오류의 성능이 가장 낮았다. 또한, 예제를 더 많이 제공할수록 전체적인 모델의 성능이 향상되었으나, 제로샷의 경우보다 오류 유형 간의 성능 차이가 커지는 것을 관찰할 수 있었다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.217-221
• /
• 2023

최근 몇 년 동안, Large Language Model(LLM)의 발전은 인공 지능 연구 분야에서 주요 도약을 이끌어 왔다. 이러한 모델들은 복잡한 자연어처리 작업에서 뛰어난 성능을 보이고 있다. 특히 Human Alignment를 위해 Supervised Fine Tuning, Reinforcement Learning, Chain-of-Hindsight 등을 적용한 언어모델이 관심 받고 있다. 본 논문에서는 위에 언급한 3가지 지시학습 방법인 Supervised Fine Tuning, Reinforcement Learning, Chain-of-Hindsight 를 Llama, OPT 모델에 적용하여 성능을 측정 및 비교한다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.690-693
• /
• 2023

언어 모델의 파라미터 수의 지속적인 증가로 100B 단위의 거대 언어모델 LLM(Large Language Model)을 구성 할 정도로 언어 모델의 크기는 증가 해 왔다. 이런 모델의 크기와 함께 성장한 다양한 Task의 작업 성능의 향상과 함께, 발전에는 환각(Hallucination) 및 윤리적 문제도 함께 떠오르고 있다. 이러한 문제 중 특히 환각 문제는 모델이 존재하지도 않는 정보를 실제 정보마냥 생성한다. 이러한 잘못된 정보 생성은 훌륭한 성능의 LLM에 신뢰성 문제를 야기한다. 환각 문제는 정보 검색을 통하여 입력 혹은 내부 표상을 증강하면 증상이 완화 되고 추가적으로 성능이 향상된다. 본 논문에서는 한국어 질의 응답에서 검색 증강을 통하여 모델의 개선점을 확인한다.

• Journal of information and communication convergence engineering
• /
• v.22 no.1
• /
• pp.33-43
• /
• 2024

Automated text summarization (ATS) systems rely on language resources as datasets. However, creating these datasets is a complex and labor-intensive task requiring linguists to extensively annotate the data. Consequently, certain public datasets for ATS, particularly in languages such as Thai, are not as readily available as those for the more popular languages. The primary objective of the ATS approach is to condense large volumes of text into shorter summaries, thereby reducing the time required to extract information from extensive textual data. Owing to the challenges involved in preparing language resources, publicly accessible datasets for Thai ATS are relatively scarce compared to those for widely used languages. The goal is to produce concise summaries and accelerate the information extraction process using vast amounts of textual input. This study introduced ThEconSum, an ATS architecture specifically designed for Thai language, using economy-related data. An evaluation of this research revealed the significant remaining tasks and limitations of the Thai language.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.129-164
• /
• 2023

In a situation where the use and introduction of Large Language Models (LLMs) is expanding due to recent developments in generative AI technology, it is difficult to find actual application cases or implementation methods for the use of internal company data in existing studies. Accordingly, this study presents a method of implementing generative AI services using the LLM application architecture using the most widely used LangChain framework. To this end, we reviewed various ways to overcome the problem of lack of information, focusing on the use of LLM, and presented specific solutions. To this end, we analyze methods of fine-tuning or direct use of document information and look in detail at the main steps of information storage and retrieval methods using the retrieval augmented generation (RAG) model to solve these problems. In particular, similar context recommendation and Question-Answering (QA) systems were utilized as a method to store and search information in a vector store using the RAG model. In addition, the specific operation method, major implementation steps and cases, including implementation source and user interface were presented to enhance understanding of generative AI technology. This has meaning and value in enabling LLM to be actively utilized in implementing services within companies.