Kisu Yang

Kisu Yang

Auto-generated profile, based on publicly available information

Kisu Yang

VAIV corp South Korea

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 February 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
CLChanhee Lee
Chanhee Lee
KYKisu Yang
Kisu Yang
TWTaesun Whang
Taesun Whang
CPChanjun Park
Chanjun Park
AMAndrew Matteson
Andrew Matteson
HLHeuiSeok Lim
HeuiSeok Lim
Language model pretraining is an effective method for improving the performance of downstream natural language processing tasks. Even though language modeling is unsupervised and thus collecting data for it is relatively less expensive, it is still a challenging process for languages with limited resources. This results in great technological disparity between high- and low-resource languages for numerous downstream natural language processing tasks. In this paper, we aim to make this technology more accessible by enabling data efficient training of pretrained language models. It is achieved by formulating language modeling of low-resource languages as a domain adaptation task using transformer-based language models pretrained on corpora of high-resource languages. Our novel cross-lingual post-training approach selectively reuses parameters of the language model trained on a high-resource language and post-trains them while learning language-specific parameters in the low-resource language. We also propose implicit translation layers that can learn linguistic differences between languages at a sequence level. To evaluate our method, we post-train a RoBERTa model pretrained in English and conduct a case study for the Korean language. Quantitative results from intrinsic and extrinsic evaluations show that our method outperforms several massively multilingual and monolingual pretrained language models in most settings and improves the data efficiency by a factor of up to 32 compared to monolingual training.

28 December 2021 in IEEE Access
Verified
Journal Article
Open access
SLSeolhwa Lee
Seolhwa Lee
KYKisu Yang
Kisu Yang
CPChanjun Park
Chanjun Park
JSJoao Sedoc
Joao Sedoc
HLHeuiSeok Lim
HeuiSeok Lim
Abstractive dialogue summarization is a challenging task for several reasons. First, most of the key information in a conversation is scattered across utterances through multi-party interactions with different textual styles. Second, dialogues are often informal structures, wherein different individuals express personal perspectives, unlike text summarization, tasks that usually target formal documents such as news articles. To address these issues, we focused on the association between utterances from individual speakers and unique syntactic structures. Speakers have unique textual styles that can contain linguistic information, such as voiceprint. To do this, we used ad-hoc analysis to explore speakers’ text styles and constructed a syntax-aware model by leveraging linguistic information (i.e., POS tagging), which alleviates the above issues by inherently distinguishing utterances from individual speakers. Our approach allows for both data and model-centric investigation. Also, we employed multi-task learning of both syntax-aware information and dialogue summarization. To the best of our knowledge, our approach is the first method to apply multi-task learning to the dialogue summarization task. Experiments on a SAMSum corpus (a large-scale dialogue summarization corpus) demonstrated that our method improved upon the vanilla model. Consequently, we found that our efforts of syntax-aware approach have been reflected by the model.

5 September 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
JSJaehyung Seo
Jaehyung Seo
SJSeungwon Jeong
Seungwon Jeong
SESugyeong Eo
Sugyeong Eo
CPChanjun Park
Chanjun Park
KYKisu Yang
Kisu Yang
HLHeuiseok Lim
Heuiseok Lim

1 January 2022
Verified
Conference Paper
Open access
PDF file
CPChanjun Park
Chanjun Park
YJYoonna Jang
Yoonna Jang
SLSeolhwa Lee
Seolhwa Lee
JSJaehyung Seo
Jaehyung Seo
KYKisu Yang
Kisu Yang
HLHeui-Seok Lim
Heui-Seok Lim
Chanjun Park, Yoonna Jang, Seolhwa Lee, Jaehyung Seo, Kisu Yang, Heuiseok Lim. Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations. 2022.

1 January 2023
Verified
Conference Paper
Open access
PDF file
KYKisu Yang
Kisu Yang
Kisu Yang. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

24 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
CPChanjun Park
Chanjun Park
YJYoonna Jang
Yoonna Jang
SLSeolhwa Lee
Seolhwa Lee
JSJaehyung Seo
Jaehyung Seo
KYKisu Yang
Kisu Yang
HLHeuiSeok Lim
HeuiSeok Lim
Augmentative and alternative communication (AAC) is a practical means of communication for people with language disabilities. In this study, we propose PicTalky, which is an AI-based AAC system that helps children with language developmental disabilities to improve their communication skills and language comprehension abilities. PicTalky can process both text and pictograms more accurately by connecting a series of neural-based NLP modules. Moreover, we perform quantitative and qualitative analyses on the essential features of PicTalky. It is expected that those suffering from language problems will be able to express their intentions or desires more easily and improve their quality of life by using this service. We have made the models freely available alongside a demonstration of the Web interface. Furthermore, we implemented robotics AAC for the first time by applying PicTalky to the NAO robot.