Jimin Sun

jimins2@cs.cmu.edu

I’m a Master’s student in Language Technologies at Carnegie Mellon University, where I am fortunate to be advised by Prof. Jean Oh.

My research interests are in the area of natural language processing. I am especially fascinated by language pragmatics, how linguistic meaning is affected by context and communicative goals. I am interested in modeling contextual information to disambiguate meaning, so that we can improve both text-driven tasks (e.g., machine translation) and multimodal tasks (e.g., visual-language navigation).

Before joining CMU, I was a research intern at Kakao Enterprise, South Korea. I previously received my Bachelor’s degree in Psychology and Master’s degree in Industrial Engineering from Seoul National University.

news

Aug 30, 2021	I started my Master’s program at CMU LTI!

publications

Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks

Sun, Jimin, Ahn, Hwijeen, Park, Chan Young, Tsvetkov, Yulia, and Mortensen, David R.

In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume 2021

Abs

Much work in cross-lingual transfer learning explored how to select better transfer languages for multilingual tasks, primarily focusing on typological and genealogical similarities between languages. We hypothesize that these measures of linguistic proximity are not enough when working with pragmatically-motivated tasks, such as sentiment analysis. As an alternative, we introduce three linguistic features that capture cross-cultural similarities that manifest in linguistic patterns and quantify distinct aspects of language pragmatics: language context-level, figurative language, and the lexification of emotion concepts. Our analyses show that the proposed pragmatic features do capture cross-cultural similarities and align well with existing work in sociolinguistics and linguistic anthropology. We further corroborate the effectiveness of pragmatically-driven transfer in the downstream task of choosing transfer languages for cross-lingual sentiment analysis.
NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer

Ahn, Hwijeen, Sun, Jimin, Park, Chan Young, and Seo, Jungyun

In Proceedings of the Fourteenth Workshop on Semantic Evaluation 2020

Abs

This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual transfer with data selection. Leveraging the semi-supervised dataset resulted in performance improvements compared to the baseline trained solely with the manually-annotated dataset. We propose a new metric, Translation Embedding Distance, to measure the transferability of instances for cross-lingual data selection. We also introduce various preprocessing steps tailored for social media text along with methods to fine-tune the pre-trained multilingual BERT (mBERT) for offensive language identification. Our multilingual systems achieved competitive results in Greek, Danish, and Turkish at OffensEval 2020.