Jeesoo Bang


2024

pdf bib
Kosmic: Korean Text Similarity Metric Reflecting Honorific Distinctions
Yerin Hwang | Yongil Kim | Hyunkyung Bae | Jeesoo Bang | Hwanhee Lee | Kyomin Jung
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Existing English-based text similarity measurements primarily focus on the semantic dimension, neglecting the unique linguistic attributes found in languages like Korean, where honorific expressions are explicitly integrated. To address this limitation, this study proposes Kosmic, a novel Korean text-similarity metric that encompasses the semantic and tonal facets of a given text pair. For the evaluation, we introduce a novel benchmark annotated by human experts, empirically showing that Kosmic outperforms the existing method. Moreover, by leveraging Kosmic, we assess various Korean paraphrasing methods to determine which techniques are most effective in preserving semantics and tone.

2023

pdf bib
Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources
Yerin Hwang | Yongil Kim | Hyunkyung Bae | Hwanhee Lee | Jeesoo Bang | Kyomin Jung
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

To address the data scarcity issue in Conversational question answering (ConvQA), a dialog inpainting method, which utilizes documents to generate ConvQA datasets, has been proposed. However, the original dialog inpainting model is trained solely on the dialog reconstruction task, resulting in the generation of questions with low contextual relevance due to insufficient learning of question-answer alignment. To overcome this limitation, we propose a novel framework called Dialogizer, which has the capability to automatically generate ConvQA datasets with high contextual relevance from textual sources. The framework incorporates two training tasks: question-answer matching (QAM) and topic-aware dialog generation (TDG). Moreover, re-ranking is conducted during the inference phase based on the contextual relevance of the generated questions. Using our framework, we produce four ConvQA datasets by utilizing documents from multiple domains as the primary source. Through automatic evaluation using diverse metrics, as well as human evaluation, we validate that our proposed framework exhibits the ability to generate datasets of higher quality compared to the baseline dialog inpainting model.

2015

pdf bib
Exploiting knowledge base to generate responses for natural language dialog listening agents
Sangdo Han | Jeesoo Bang | Seonghan Ryu | Gary Geunbae Lee
Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue