scispace - formally typeset
Search or ask a question
Author

Sungjoon Park

Bio: Sungjoon Park is an academic researcher from KAIST. The author has contributed to research in topics: Turbo code & Language model. The author has an hindex of 11, co-authored 29 publications receiving 298 citations.

Papers
More filters
Proceedings ArticleDOI
Sungjoon Park1, JinYeong Bak1, Alice Oh1
01 Sep 2017
TL;DR: This work applies several rotation algorithms to the vector representation of words to improve the interpretability, and shows that the rotated vectors outperform the original and the sparse overcomplete vectors for interpretability and expressiveness tasks.
Abstract: Vector representation of words improves performance in various NLP tasks, but the high dimensional word vectors are very difficult to interpret We apply several rotation algorithms to the vector representation of words to improve the interpretability Unlike previous approaches that induce sparsity, the rotated vectors are interpretable while preserving the expressive performance of the original vectors Furthermore, any prebuilt word vector representation can be rotated for improved interpretability We apply rotation to skipgrams and glove and compare the expressive power and interpretability with the original vectors and the sparse overcomplete vectors The results show that the rotated vectors outperform the original and the sparse overcomplete vectors for interpretability and expressiveness tasks

51 citations

Proceedings ArticleDOI
07 May 2016
TL;DR: In this paper, the authors define a similarity space to operationalize team design constructs about role proficiency, generality, and congruency, and conduct focus groups with novice and elite players to understand how players' team design practices vary with expertise.
Abstract: Multiplayer online battle arena games provide an excellent opportunity to study team performance. When designing a team, players must negotiate a proficiency-congruency dilemma between selecting roles that best match their experience and roles that best complement the existing roles on the team. We adopt a mixed-methods approach to explore how players negotiate this dilemma. Using data from League of Legends, we define a similarity space to operationalize team design constructs about role proficiency, generality, and congruency. We collect publicly available data from 3.36 million players to test the influence of these constructs on team performance. We also conduct focus groups with novice and elite players to understand how players' team design practices vary with expertise. We find that the two factors, player proficiency and team congruency, both increase team performance, with the former having a stronger impact. We also find that elite players are better at balancing the two factors than the novice players. These findings have implications for players, designers, and theorists about how to recommend team designs that jointly prioritize individuals' expertise and teams' compatibility.

49 citations

Proceedings ArticleDOI
Sungjoon Park1, Jeongmin Byun1, Sion Baek, Yongseok Cho, Alice Oh1 
01 Jul 2018
TL;DR: This paper decomposes Korean words into the jamo-level, beyond the character- level, allowing a systematic use of subword information, and shows that the simple method outperforms word2vec and character-level Skip-Grams on semantic and syntactic similarity and analogy tasks and contributes positively toward downstream NLP tasks such as sentiment analysis.
Abstract: Research on distributed word representations is focused on widely-used languages such as English. Although the same methods can be used for other languages, language-specific knowledge can enhance the accuracy and richness of word vector representations. In this paper, we look at improving distributed word representations for Korean using knowledge about the unique linguistic structure of Korean. Specifically, we decompose Korean words into the jamo-level, beyond the character-level, allowing a systematic use of subword information. To evaluate the vectors, we develop Korean test sets for word similarity and analogy and make them publicly available. The results show that our simple method outperforms word2vec and character-level Skip-Grams on semantic and syntactic similarity and analogy tasks and contributes positively toward downstream NLP tasks such as sentiment analysis.

39 citations

Journal ArticleDOI
Dongsoo Han1, Minkyu Lee1, Sungjoon Park1
TL;DR: The more u-health services are developed in THE-MUSS, the better services it can provide in the future, and it is confirmed that the system is practically useful for mobile u- health services by developing mobile stress and weight management services on THE- MUSS.

33 citations

Journal ArticleDOI
12 May 2016-PLOS ONE
TL;DR: Evidence is found for a complexity barrier whereby editors are less likely to edit complex content in a second language and multilinguals are less engaged and show lower levels of language proficiency in their second languages.
Abstract: Multilingualism is common offline, but we have a more limited understanding of the ways multilingualism is displayed online and the roles that multilinguals play in the spread of content between speakers of different languages. We take a computational approach to studying multilingualism using one of the largest user-generated content platforms, Wikipedia. We study multilingualism by collecting and analyzing a large dataset of the content written by multilingual editors of the English, German, and Spanish editions of Wikipedia. This dataset contains over two million paragraphs edited by over 15,000 multilingual users from July 8 to August 9, 2013. We analyze these multilingual editors in terms of their engagement, interests, and language proficiency in their primary and non-primary (secondary) languages and find that the English edition of Wikipedia displays different dynamics from the Spanish and German editions. Users primarily editing the Spanish and German editions make more complex edits than users who edit these editions as a second language. In contrast, users editing the English edition as a second language make edits that are just as complex as the edits by users who primarily edit the English edition. In this way, English serves a special role bringing together content written by multilinguals from many language editions. Nonetheless, language remains a formidable hurdle to the spread of content: we find evidence for a complexity barrier whereby editors are less likely to edit complex content in a second language. In addition, we find that multilinguals are less engaged and show lower levels of language proficiency in their second languages. We also examine the topical interests of multilingual editors and find that there is no significant difference between primary and non-primary editors in each language.

31 citations


Cited by
More filters
Journal ArticleDOI
01 Jun 1959

3,442 citations

01 Aug 2001
TL;DR: The study of distributed systems which bring to life the vision of ubiquitous computing systems, also known as ambient intelligence, is concentrated on in this work.
Abstract: With digital equipment becoming increasingly networked, either on wired or wireless networks, for personal and professional use alike, distributed software systems have become a crucial element in information and communications technologies. The study of these systems forms the core of the ARLES' work, which is specifically concerned with defining new system software architectures, based on the use of emerging networking technologies. In this context, we concentrate on the study of distributed systems which bring to life the vision of ubiquitous computing systems, also known as ambient intelligence.

2,774 citations

01 Jan 2016
TL;DR: The applied missing data analysis is universally compatible with any devices to read and is available in the digital library an online access to it is set as public so you can download it instantly.
Abstract: Thank you for downloading applied missing data analysis. Maybe you have knowledge that, people have look hundreds times for their favorite readings like this applied missing data analysis, but end up in infectious downloads. Rather than enjoying a good book with a cup of tea in the afternoon, instead they juggled with some malicious bugs inside their laptop. applied missing data analysis is available in our digital library an online access to it is set as public so you can download it instantly. Our digital library hosts in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Merely said, the applied missing data analysis is universally compatible with any devices to read.

1,924 citations

ReportDOI
01 Jan 1967

890 citations

Posted Content
TL;DR: The resulting approach offers a way to be more systematic and transparent in the treatment of scientific and technological diversity in a range of fields, including conservation management, research governance, energy policy and sustainable innovation.
Abstract: This paper addresses the scope for more integrated general analysis of diversity in science, technology and society. It proposes a framework recognizing three necessary but individually insufficient properties of diversity. Based on 10 quality criteria, it suggests a general quantitative non-parametric diversity heuristic. This allows the systematic exploration of diversity under different perspectives, including divergent conceptions of relevant attributes and contrasting weightings on different diversity properties. It is shown how this heuristic may be used to explore different possible trade-offs between diversity and other aspects of interest, including portfolio interactions. The resulting approach offers a way to be more systematic and transparent in the treatment of scientific and technological diversity in a range of fields, including conservation management, research governance, energy policy and sustainable innovation.

730 citations