Hyunjae Kim


2024

pdf bib
Fine-tuning CLIP Text Encoders with Two-step Paraphrasing
Hyunjae Kim | Seunghyun Yoon | Trung Bui | Handong Zhao | Quan Tran | Franck Dernoncourt | Jaewoo Kang
Findings of the Association for Computational Linguistics: EACL 2024

Contrastive language-image pre-training (CLIP) models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval, where the model is required to effectively process natural language input to produce an accurate visual output. However, current models still face limitations in dealing with linguistic variations in input queries, such as paraphrases, making it challenging to handle a broad range of user queries in real-world applications. In this study, we introduce a straightforward fine-tuning approach to enhance the representations of CLIP models for paraphrases. Our approach involves a two-step paraphrase generation process, where we automatically create two categories of paraphrases from web-scale image captions by leveraging large language models. Subsequently, we fine-tune the CLIP text encoder using these generated paraphrases while freezing the image encoder. Our resulting model, which we call ParaCLIP, exhibits significant improvements over baseline CLIP models across various tasks, including paraphrased retrieval (with rank similarity scores improved by up to 7.6% and 9.6%), Visual Genome Relation and Attribution, as well as seven semantic textual similarity tasks.

2023

pdf bib
KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization
Gangwoo Kim | Hajung Kim | Lei Ji | Seongsu Bae | Chanhwi Kim | Mujeen Sung | Hyunjae Kim | Kun Yan | Eric Chang | Jaewoo Kang
The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks

In this paper, we introduce CheXOFA, a new pre-trained vision-language model (VLM) for the chest X-ray domain. Our model is initially pre-trained on various multimodal datasets within the general domain before being transferred to the chest X-ray domain. Following a prominent VLM, we unify various domain-specific tasks into a simple sequence-to-sequence schema. It enables the model to effectively learn the required knowledge and skills from limited resources in the domain. Demonstrating superior performance on the benchmark datasets provided by the BioNLP shared task (Delbrouck et al., 2023), our model benefits from its training across multiple tasks and domains. With subtle techniques including ensemble and factual calibration, our system achieves first place on the RadSum23 leaderboard for the hidden test set.

pdf bib
Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations
Hyunjae Kim | Jaehyo Yoo | Seunghyun Yoon | Jaewoo Kang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Most weakly supervised named entity recognition (NER) models rely on domain-specific dictionaries provided by experts. This approach is infeasible in many domains where dictionaries do not exist. While a phrase retrieval model was used to construct pseudo-dictionaries with entities retrieved from Wikipedia automatically in a recent study, these dictionaries often have limited coverage because the retriever is likely to retrieve popular entities rather than rare ones. In this study, we present a novel framework, HighGEN, that generates NER datasets with high-coverage pseudo-dictionaries. Specifically, we create entity-rich dictionaries with a novel search method, called phrase embedding search, which encourages the retriever to search a space densely populated with various entities. In addition, we use a new verification process based on the embedding distance between candidate entity mentions and entity types to reduce the false-positive noise in weak labels generated by high-coverage dictionaries. We demonstrate that HighGEN outperforms the previous best model by an average F1 score of 4.7 across five NER benchmark datasets.

2022

pdf bib
KU_ED at SocialDisNER: Extracting Disease Mentions in Tweets Written in Spanish
Antoine Lain | Wonjin Yoon | Hyunjae Kim | Jaewoo Kang | Ian Simpson
Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task

This paper describes our system developed for the Social Media Mining for Health (SMM4H) 2022 SocialDisNER task. We used several types of pre-trained language models, which are trained on Spanish biomedical literature or Spanish Tweets. We showed the difference in performance depending on the quality of the tokenization as well as introducing silver standard annotations when training the model. Our model obtained a strict F1 of 80.3% on the test set, which is an improvement of +12.8% F1 (24.6 std) over the average results across all submissions to the SocialDisNER challenge.

pdf bib
Simple Questions Generate Named Entity Recognition Datasets
Hyunjae Kim | Jaehyo Yoo | Seunghyun Yoon | Jinhyuk Lee | Jaewoo Kang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Recent named entity recognition (NER) models often rely on human-annotated datasets requiring the vast engagement of professional knowledge on the target domain and entities. This work introduces an ask-to-generate approach, which automatically generates NER datasets by asking simple natural language questions to an open-domain question answering system (e.g., “Which disease?”). Despite using fewer training resources, our models solely trained on the generated datasets largely outperform strong low-resource models by 19.5 F1 score across six popular NER benchmarks. Our models also show competitive performance with rich-resource models that additionally leverage in-domain dictionaries provided by domain experts. In few-shot NER, we outperform the previous best model by 5.2 F1 score on three benchmarks and achieve new state-of-the-art performance.

2021

pdf bib
“Killing Me” Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism
Buru Chang | Inggeol Lee | Hyunjae Kim | Jaewoo Kang
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Several machine learning-based spoiler detection models have been proposed recently to protect users from spoilers on review websites. Although dependency relations between context words are important for detecting spoilers, current attention-based spoiler detection models are insufficient for utilizing dependency relations. To address this problem, we propose a new spoiler detection model called SDGNN that is based on syntax-aware graph neural networks. In the experiments on two real-world benchmark datasets, we show that our SDGNN outperforms the existing spoiler detection models.

pdf bib
Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering
Gangwoo Kim | Hyunjae Kim | Jungsoo Park | Jaewoo Kang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

One of the main challenges in conversational question answering (CQA) is to resolve the conversational dependency, such as anaphora and ellipsis. However, existing approaches do not explicitly train QA models on how to resolve the dependency, and thus these models are limited in understanding human dialogues. In this paper, we propose a novel framework, ExCorD (Explicit guidance on how to resolve Conversational Dependency) to enhance the abilities of QA models in comprehending conversational context. ExCorD first generates self-contained questions that can be understood without the conversation history, then trains a QA model with the pairs of original and self-contained questions using a consistency-based regularizer. In our experiments, we demonstrate that ExCorD significantly improves the QA models’ performance by up to 1.2 F1 on QuAC, and 5.2 F1 on CANARD, while addressing the limitations of the existing approaches.

2020

pdf bib
Look at the First Sentence: Position Bias in Question Answering
Miyoung Ko | Jinhyuk Lee | Hyunjae Kim | Gangwoo Kim | Jaewoo Kang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Many extractive question answering models are trained to predict start and end positions of answers. The choice of predicting answers as positions is mainly due to its simplicity and effectiveness. In this study, we hypothesize that when the distribution of the answer positions is highly skewed in the training set (e.g., answers lie only in the k-th sentence of each passage), QA models predicting answers as positions can learn spurious positional cues and fail to give answers in different positions. We first illustrate this position bias in popular extractive QA models such as BiDAF and BERT and thoroughly examine how position bias propagates through each layer of BERT. To safely deliver position information without position bias, we train models with various de-biasing methods including entropy regularization and bias ensembling. Among them, we found that using the prior distribution of answer positions as a bias model is very effective at reducing position bias, recovering the performance of BERT from 37.48% to 81.64% when trained on a biased SQuAD dataset.

2018

pdf bib
Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering
Jinhyuk Lee | Seongjun Yun | Hyunjae Kim | Miyoung Ko | Jaewoo Kang
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Recently, open-domain question answering (QA) has been combined with machine comprehension models to find answers in a large knowledge source. As open-domain QA requires retrieving relevant documents from text corpora to answer questions, its performance largely depends on the performance of document retrievers. However, since traditional information retrieval systems are not effective in obtaining documents with a high probability of containing answers, they lower the performance of QA systems. Simply extracting more documents increases the number of irrelevant documents, which also degrades the performance of QA systems. In this paper, we introduce Paragraph Ranker which ranks paragraphs of retrieved documents for a higher answer recall with less noise. We show that ranking paragraphs and aggregating answers using Paragraph Ranker improves performance of open-domain QA pipeline on the four open-domain QA datasets by 7.8% on average.