Search Results for author: Wonsuk Yang

Found 12 papers, 6 papers with code

GeezSwitch: Language Identification in Typologically Related Low-resourced East African Languages

1 code implementation LREC 2022 Fitsum Gaim, Wonsuk Yang, Jong C. Park

Language identification is one of the fundamental tasks in natural language processing that is a prerequisite to data processing and numerous applications.

Language Identification Machine Translation

Query Generation with External Knowledge for Dense Retrieval

no code implementations DeeLIO (ACL) 2022 Sukmin Cho, Soyeong Jeong, Wonsuk Yang, Jong Park

The dense retriever with the queries requiring implicit information is found to make good performance improvement.

Language Modelling Retrieval

Fashion Style Editing with Generative Human Prior

no code implementations2 Apr 2024 Chaerin Kong, Seungyong Lee, Soohyeok Im, Wonsuk Yang

Image editing has been a long-standing challenge in the research community with its far-reaching impact on numerous applications.

A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning

1 code implementation22 Mar 2022 Hugo Berg, Siobhan Mackenzie Hall, Yash Bhalgat, Wonsuk Yang, Hannah Rose Kirk, Aleksandar Shtedritski, Max Bain

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation.

Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\circ$ Videos

1 code implementation11 Oct 2021 Heeseung Yun, Youngjae Yu, Wonsuk Yang, Kangil Lee, Gunhee Kim

However, previous benchmark tasks for panoramic videos are still limited to evaluate the semantic understanding of audio-visual relationships or spherical spatial property in surroundings.

Audio-visual Question Answering Question Answering +2

Generating Negative Samples by Manipulating Golden Responses for Unsupervised Learning of a Response Evaluation Model

1 code implementation NAACL 2021 ChaeHun Park, Eugene Jang, Wonsuk Yang, Jong Park

Reference-based metrics that rely on comparisons to a set of known correct responses often fail to account for this variety, and consequently correlate poorly with human judgment.

Dialogue Evaluation

Pano-AVQA: Grounded Audio-Visual Question Answering on 360deg Videos

1 code implementation ICCV 2021 Heeseung Yun, Youngjae Yu, Wonsuk Yang, Kangil Lee, Gunhee Kim

However, previous benchmark tasks for panoramic videos are still limited to evaluate the semantic understanding of audio-visual relationships or spherical spatial property in surroundings.

Audio-visual Question Answering Question Answering +2

Generating Sentential Arguments from Diverse Perspectives on Controversial Topic

1 code implementation WS 2019 ChaeHun Park, Wonsuk Yang, Jong Park

Considering diverse aspects of an argumentative issue is an essential step for mitigating a biased opinion and making reasonable decisions.

Retrieval

Computer Assisted Annotation of Tension Development in TED Talks through Crowdsourcing

no code implementations WS 2019 Seungwon Yoon, Wonsuk Yang, Jong Park

For the crowdsourced environment, we compared the annotation results with and without our method of machine-assisted annotation.

Extraction of Gene-Environment Interaction from the Biomedical Literature

no code implementations IJCNLP 2017 Jinseon You, Jin-Woo Chung, Wonsuk Yang, Jong C. Park

Genetic information in the literature has been extensively looked into for the purpose of discovering the etiology of a disease.

Named Entity Recognition (NER)

Cannot find the paper you are looking for? You can Submit a new open access paper.