Papers by Jaegul Choo

Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models (2024.findings-acl)

Challenge:	Existing studies focus on generating SQL codes from natural language questions . however, questions cover more diverse tasks including table manipulation or performance issues .
Approach:	They propose a task to generate pSQL codes from natural language questions . they define two new metrics suitable for the task, Canonical-BLEU and SQL-BLUE .
Outcome:	The proposed task generates well-formed queries on under-specified database issues.

Copied to clipboard

Dohyun Lee, Daniel Rim, Minseok Choi, Jaegul Choo

AniEE: A Dataset of Animal Experimental Literature for Event Extraction (2023.findings-emnlp)

Challenge:	Language models (LMs) demonstrate exceptional capabilities on tasks, but are vulnerable to extraction attacks.
Approach:	They propose Privacy Protection via Optimal Parameters (POP) which induces the model to forget about some of its training data.
Outcome:	The proposed method outperforms the state-of-the-art in retaining LM performance on 9 classification and 4 dialogue benchmarks.

Copied to clipboard

Dohee Kim, Ra Yoo, Soyoung Yang, Hee Yang, Jaegul Choo

Information Extraction & Text Mining

Challenge:	Event extraction (EE) is a crucial information extraction task in biomedical domain . existing biomedically EE datasets focus on cell experiments or overall procedures .
Approach:	They propose an animal experiment customized entity and event scheme for event extraction . they create an expert-annotated high-quality dataset containing discontinuous entities and nested events .
Outcome:	The proposed dataset is based on the animal experiment stage and a NER and EE model.

Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning (2021.acl-long)

Copied to clipboard

Cheonbok Park, Yunwon Tae, TaeHee Kim, Soyoung Yang, Mohammad Azam Khan, Lucy Park, Jaegul Choo

Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering (2024.findings-acl)

Challenge:	Unsupervised machine translation suffers from data-scarce domains, authors report . a meta-learning algorithm trains the model to adapt to another domain by utilizing only a small amount of training data.
Approach:	They propose a meta-learning algorithm that trains the model to adapt to another domain . their model surpasses a transfer learning-based approach by up to 2-3 BLEU scores .
Outcome:	The proposed algorithm outperforms a transfer learning-based approach by 2-3 BLEU scores . the proposed model outperformed previous models in the domain of unsupervised machine translation .

Copied to clipboard

ChaeHun Park, Koanho Lee, Hyesu Lim, Jaeseok Kim, Junmo Park, Yu-Jung Heo, Du-Seong Chang, Jaegul Choo

Multilinguality

Challenge:	Recent studies have employed machine translation systems for cross-lingual VQA tasks . however, translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts.
Approach:	They propose a machine translation system that can train models in multiple languages . they propose augmentation strategies that reduce translation artifacts in translated texts .
Outcome:	The proposed approach reduces translation artifacts in models across languages and languages.

Exploring In-context Example Generation for Machine Translation (2025.findings-acl)

Copied to clipboard

Dohyun Lee, Seungil Chad Lee, Chanwoo Yang, Yujin Baek, Jaegul Choo

Learning to Generate Questions by Learning to Recover Answer-containing Sentences (2021.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated strong performance across various tasks with just a few examples.
Approach:	They propose a method that generates in-context example pairs without external resources.
Outcome:	The proposed method builds upon two prior criteria, relevance and diversity, which have been highlighted as key factors for in-context example selection.

Copied to clipboard

Seohyun Back, Akhil Kedia, Sai Chetan Chinthakindi, Haejun Lee, Jaegul Choo

Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling (2024.findings-emnlp)

Challenge:	Recent research has focused on synthetically generating a question from a given context and an annotated answer by training an additional generative model.
Approach:	They propose a method that learns to generate contextually rich questions by recovering answer-containing sentences.
Outcome:	The proposed approach improves the quality and accuracy of existing models and achieves comparable results to the state-of-the-art on MS MARCO and NewsQA.

Copied to clipboard

Daehoon Gwak, Junwoo Park, Minho Park, ChaeHun Park, Hyunchan Lee, Edward Choi, Jaegul Choo

Challenge:	Existing approaches for text-based event prediction are limited in quality due to dynamic nature of international relations and conflicting economic dynamics.
Approach:	They propose a novel dataset that leverages the advanced reasoning capabilities of large-language models to address these limitations.
Outcome:	The proposed dataset features high-quality scoring labels generated through advanced prompt modeling and rigorously validated by domain experts in political science.

HistRED: A Historical Document-Level Relation Extraction Dataset (2023.acl-long)

Copied to clipboard

Soyoung Yang, Minseok Choi, Youngwoo Cho, Jaegul Choo

Information Extraction & Text Mining

Challenge:	Relation extraction (RE) tasks are limited to sentencelevel RE, but are not feasible in real-world applications.
Approach:	They propose a bilingual relation extraction model that leverages both Korean and Hanja contexts to predict relations between entities.
Outcome:	The proposed model outperforms monolingual baselines on histRED . it supports various self-contained subtexts with different lengths .

Single Ground Truth Is Not Enough: Adding Flexibility to Aspect-Based Sentiment Analysis Evaluation (2025.naacl-long)

Copied to clipboard

Soyoung Yang, Hojun Cho, Jiyoung Lee, Sohee Yoon, Edward Choi, Jaegul Choo, Won Ik Cho

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis (ABSA) is a challenging task of extracting sentiments along with their corresponding aspects and opinion terms from text.
Approach:	They propose a pipeline that expands existing evaluation sets by adding alternative valid terms for aspect and opinion.
Outcome:	The proposed evaluation set uncovers the capabilities of large language models (LLMs) in ABSA tasks, which is concealed by the single-answer GT sets.

Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation (2026.findings-acl)

Copied to clipboard

Kyudan Jung, Hojun Cho, Jooyeol Yun, Soyoung Yang, Jaehyeok Jang, Jaegul Choo

Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task (2022.emnlp-main)

Challenge:	Talk-to-Your-Slides is a high-efficiency slide editing agent that uses language-driven structured data manipulation instead of the image modality.
Approach:	They propose a language-driven slide editing agent that uses language-based structured data manipulation instead of image modality.
Outcome:	The proposed system achieves faster processing and better instruction fidelity than GUI-based agents.

Copied to clipboard

Nyoungwoo Lee, ChaeHun Park, Ho-Jin Choi, Jaegul Choo

Responsible & Trustworthy NLP

Challenge:	Existing methods for synthesizing adversarial negative responses are limited by their scalability and cost.
Approach:	They propose a method for generating adversarial negative responses using a large-scale language model.
Outcome:	The proposed method outperforms other methods on dialogue selection tasks.

Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models (2026.acl-industry)

Copied to clipboard

Kyudan Jung, Jihwan Kim, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park

Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration (2025.acl-long)

Challenge:	Existing high-quality conversational data is limited for full-duplex models . overlapping and backchanneling are a challenge for most systems .
Approach:	They propose a robust and scalable open-source data processing pipeline for full-duplex models.
Outcome:	The proposed pipeline can listen and speak simultaneously, supporting more fluid and human-like interaction.

Copied to clipboard

ChaeHun Park, Yujin Baek, Jaeseok Kim, Yu-Jung Heo, Du-Seong Chang, Jaegul Choo

Explainability & Interpretability in NLP

Challenge:	Existing approaches to creating inclusive vision-language models rely on human annotators, making it labor-intensive and creating cognitive burdens.
Approach:	They propose a semi-automated framework for constructing cultural VLM benchmarks . they use an annotated sample of Korean culture to generate questions .
Outcome:	The proposed framework is based on a Korean culture dataset and shows that open-source models lag behind proprietary ones in understanding Korean culture.

SimCKP: Simple Contrastive Learning of Keyphrase Representations (2023.findings-emnlp)

Copied to clipboard

Minseok Choi, Chaeheon Gwak, Seho Kim, Si Kim, Jaegul Choo

PePe: Personalized Post-editing Model utilizing User-generated Post-edits (2023.findings-eacl)

Challenge:	Existing models for keyphrase generation and keyphrase extraction use a token level to generate keyphrases that do not appear in a document.
Approach:	They propose a simple contrastive learning framework that generates keyphrases that do not appear in a document and a reranker that adapts the scores for each generated phrase.
Outcome:	The proposed model outperforms the state-of-the-art models on multiple benchmark datasets.

Copied to clipboard

Jihyeon Lee, Taehee Kim, Yunwon Tae, Cheonbok Park, Jaegul Choo

AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain (2021.emnlp-main)

Challenge:	Existing neural machine translation models ignore personal style in their translations, but in these studies the definition of personal style is over-simplified.
Approach:	They propose a personalized automatic post-editing framework that generates sentences considering distinct personal behaviors by collecting post-edited data from a live machine translation system and combining a discriminator module and user-specific parameters.
Outcome:	The proposed model outperforms baseline models on four different metrics including BLEU, TER, YiSi-1, and human evaluation.

Copied to clipboard

Jimin Hong, TaeHee Kim, Hyesu Lim, Jaegul Choo

Evaluating Automatic Speech Recognition Systems for Korean Meteorological Experts (2025.findings-emnlp)

Challenge:	Existing methods to fine-tune a language model with a large corpus in a general domain are suboptimal for downstream data when domain discrepancy exists.
Approach:	They propose to consider the pretrained vocabulary as an optimizable parameter . they add domain specific vocabulary based on a tokenization statistic . their method achieved consistent performance improvements on diverse domains .
Outcome:	The proposed method achieves consistent performance improvements on diverse domains.

Copied to clipboard

ChaeHun Park, Hojun Cho, Jaegul Choo

Rethinking Style Transformer with Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained Model (2022.emnlp-main)

Challenge:	Using a dataset of Korean weather queries, we find that automatic speech recognition systems fail on specialized vocabulary.
Approach:	They propose an evaluation dataset of Korean weather queries . the dataset was recorded by diverse native speakers following pronunciation guidelines .
Outcome:	The proposed model reduces error rates on meteorological terms and improves overall recognition accuracy.

Copied to clipboard

Hojun Cho, Dohee Kim, Seungwoo Ryu, ChaeHun Park, Hyungjong Noh, Jeong-in Hwang, Minseok Choi, Edward Choi, Jaegul Choo

Responsible & Trustworthy NLP

Challenge:	Existing methods to train text style transfer models with adversarial loss degrade fluency compared to other metrics.
Approach:	They propose a method which leverages a pretrained language model to improve fluency by restructuring the discriminator and the model itself.
Outcome:	The proposed model achieves state-of-the-art on three public benchmarks and achieved state-outperformance on the overall metrics.

Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models (2024.findings-emnlp)

Copied to clipboard

Minseok Choi, Kyunghyun Min, Jaegul Choo

Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport (2025.acl-long)

Challenge:	Pretrained language models memorize large amounts of information, raising significant safety concerns.
Approach:	They propose an approach to machine unlearning for multilingual language models that selectively erases information across different languages while maintaining overall performance.
Outcome:	The proposed approach is compared with existing unlearning baselines and set a new standard for secure and adaptable multilingual language models.

Copied to clipboard

Minseok Choi, Daniel Rim, Dohyun Lee, Jaegul Choo

Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method (2026.findings-acl)

Challenge:	Instruction-following large language models (LLMs) inadvertently disclose private, sensitive information to their users, underscoring the need for machine unlearning techniques to remove selective information from the models.
Approach:	They propose an optimal transport-based unlearning method that utilizes the Wasserstein distance from the model’s initial parameters to achieve more effective and fine-grained unlearning.
Outcome:	The proposed method surpasses existing methods and establishes a new standard for secure and adaptable LLMs that can accommodate user data removal requests without the need for full retraining.

Copied to clipboard

Taehee Kim, Seungbin Yang, Jihwan Kim, Jaegul Choo

MemoReader: Large-Scale Reading Comprehension through Neural Memory Controller (D18-1)

Challenge:	Existing methods for retrieving relevant tables from databases are limited by the number of tables required.
Approach:	They propose an adaptive table retrieval method that adjusts the number of tables retrieved according to the requirements of each query.
Outcome:	Experiments on Spider, BIRD, and Spider 2.0 show that the proposed method improves performance and retrieval and downstream tasks.

Copied to clipboard

Seohyun Back, Seunghak Yu, Sathish Reddy Indurthi, Jihie Kim, Jaegul Choo

Machine Reading Comprehension

Challenge:	Existing approaches to machine reading comprehension are limited in understanding, up to a few paragraphs, failing to comprehend lengthy documents.
Approach:	They propose a deep neural network architecture to handle a long-range dependency in RC tasks.
Outcome:	The proposed method outperforms existing methods especially for lengthy documents.

Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs (2025.emnlp-main)

Copied to clipboard

Daehoon Gwak, Minseo Jung, Junwoo Park, Minho Park, ChaeHun Park, Junha Hyung, Jaegul Choo

Novel Natural Language Summarization of Program Code via Leveraging Multiple Input Representations (2021.findings-emnlp)

Challenge:	Masked diffusion models (MDMs) are promising non-autoregressive alternatives for large language modeling.
Approach:	They propose a method that leverages an external reward model to provide a principled global signal during the iterative diffusion process.
Outcome:	The proposed method improves non-autoregressive generation orders and performance across evaluation metrics.

Copied to clipboard

Fuxiang Chen, Mijung Kim, Jaegul Choo

Towards Formality-Aware Neural Machine Translation by Leveraging Context Information (2023.findings-emnlp)

Challenge:	Existing work on code summarization shows that code descriptions are difficult to generate for developers unfamiliar with the code base.
Approach:	They propose a multi-task approach that trains two similar tasks to generate code descriptions for each line of code.
Outcome:	The proposed model improves over baselines and achieves the new state-of-the-art.

Copied to clipboard

Dohee Kim, Yujin Baek, Soyoung Yang, Jaegul Choo

Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information (2025.emnlp-industry)

Challenge:	Formality is one of the most important linguistic properties to determine the naturalness of translation.
Approach:	They propose a method to explicitly inform neural machine translation models by pinpointing key informative tokens using a formality classifier.
Outcome:	The proposed method improves translation quality and conforms to the appropriate syntax.

Copied to clipboard

Hojun Cho, Donghu Kim, Soyoung Yang, Chan Lee, Hunjoo Lee, Jaegul Choo

Challenge:	Existing language agents powered by large language models face resource-constrained environments . proprietary models raise concerns in cost and service dependency, while large-scale open-source models require substantial computational resources.
Approach:	They propose a Korean chemical toxicity information agent that reduces token consumption . they propose 'scenario-based dialogue generation' methodology that distills tool-using capabilities from larger models.
Outcome:	The proposed language agent outperforms untuned models and baseline approaches in DB faithfulness and preference.

Reweighting Strategy Based on Synthetic Data Identification for Sentence Similarity (2022.coling-1)

Copied to clipboard

TaeHee Kim, ChaeHun Park, Jimin Hong, Radhika Dua, Edward Choi, Jaegul Choo

Revisiting LLMs as Zero-Shot Time Series Forecasters: Small Noise Can Break Large Models (2025.acl-short)

Challenge:	obtaining large amounts of human-annotated datasets to train a sentence embedding model is difficult and expensive.
Approach:	They propose to train a classifier that identifies machine-written sentences and then use it to train an embedding model on synthetic data.
Outcome:	The proposed method outperforms baselines on four real-world datasets and generalizes well.

Copied to clipboard

Junwoo Park, Hyuck Lee, Dohyun Lee, Daehoon Gwak, Jaegul Choo

DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation (2023.findings-acl)

Challenge:	Large Language Models (LLMs) have shown remarkable performance across diverse tasks without domain-specific training, fueling interest in their potential for time series forecasting.
Approach:	They evaluate the effectiveness of LLMs as zero-shot forecasters compared to state-of-the-art domain-specific models by encoding sequences directly within prompts.
Outcome:	The proposed models perform well across multiple domains while reducing the need for domain-specific training.

Copied to clipboard

ChaeHun Park, Seungil Lee, Daniel Rim, Jaegul Choo

Information Retrieval

Challenge:	Recent studies suggest that neural classifiers make overly confident predictions for examples from unseen distributions.
Approach:	They propose a new evaluation metric, DENSITY, which measures how likely a response would appear in the distribution of human conversations.
Outcome:	The proposed metric measures how likely a response would appear in the distribution of human conversations.

Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images (2021.acl-short)

Copied to clipboard

Nyoungwoo Lee, Suwon Shin, Jaegul Choo, Ho-Jin Choi, Sung-Hyon Myaeng