News

  • (2021-10) Two papers are accepted at EMNLP workshop! [workshop1] [workshop2]
  • (2021-09) I decided to join at University of Copenhagen CoAStaL NLP group 😁
  • (2021-06) Ph.D dissertation was finished! Lol
  • (2021-06) One paper is accepted at ACL workshop! [paper]
  • (2021-01) Started new project Dialogue summarization.
  • (2020-12) Preprinted "An Evaluation Protocol for Generative Conversational Systems". [arXiv]
  • (2020-12) Two papers are accepted at EMNLP workshop! [Paper 1] [Paper 2]
  • About Me

    Hello, I’m a Seolhwa, NLP researcher. I have rich experience in NLP & Deep learning techniques. Also I am good at

    • Python
    • Pytorch
    • Dynet
    • Tensorflow
    • C/C++
    • R
    • Java
    • MySQL
    • PHP
    • Javascript

    What I do

    seolhwa lee

    Abstractive dialogue summarization

    Abstractive dialogue summarization is challenging due to the most important pieces of information in a conversation are scattered across the utterances through multi-party interactions. To address this challenges, this research propose the syntax-aware sequence-to-sequence model for abstractive dialogue summarization.

    Will preprint soon
    seolhwa lee

    An Evaluation Protocol for Generative Conversational Systems

    There are a multitude of novel generative models for open domain conversational systems; however, there is no systematic evaluation of different systems. Systematic comparisons require consistency in experimental design, evaluation sets, conversational systems and their outputs, and statistical analysis. In this paper layout a protocol for the evaluation of conversational models using head-to-head pairwise comparison.

    This work conducted during visiting student at JHU.

    [Paper]

    Neuroscience with computer science

    Programming mistakes frequently waste software developers’ time and may lead to the introduction of bugs into their software, causing serious risks for their customers. Using the correlation between various software process metrics and defects, earlier work has traditionally attempted to spot such bug risks. However, this study departs from previous works in examining a more direct method of using psycho-physiological sensors data to detect the difficulty of program comprehension tasks and programmer level of expertise.

    This work cited by Microsoft Research team [Paper]

    [Paper 1] [Paper 2] [Slide]

    COVID19-QA chatbot

    To combat misinformation regarding COVID- 19 during this unprecedented pandemic, we propose a conversational agent that answers questions related to COVID-19. We adapt the Poly-encoder (Humeau et al., 2020) model for informational retrieval from FAQs. We show that after fine-tuning, the Poly-encoder can achieve a higher F1 score. We make our code publicly available for other researchers to use.

    [Paper] [Code] [Slide]

    Dialogue Breakdown Detection

    Dialogue breakdowns can lead to inappropriate utterances. Since such breakdowns sorely compromise user satisfaction regarding the system, breakdown detection is an essential task for robust dialog systems to handle false communications.

    [Paper] [Code]

    Fashion Style Recommendation model

    The text-based search method has limitations because of the nature of the fashion industry, in which design is a very important factor. Therefore, we developed an intelligent fashion technique based on deep learning for efficient fashion product searches and recommendations consisting of a Sketch-Product fashion retrieval model and vector-based user preference fashion recommendation model.

    [Paper]

    Bilingual Word Embedding

    Bilingual word embedding models focus on the induction of a shared bilingual word embedding space where words from both languages are represented in a uniform language-independent manner such that similar words have similar representation. These research goal make seed lexicon by aligned parallel data and make mapping function between seed lexicon and general-domain corpora such as Wikipedia. Therefore, we expect to applicate these research to other NLP tasks such as machine translation.

    [Demo]

    Education

    NLP & AI From Korea University

    2015 - Aug. 2021

    I received integrated Master and PhD degree in computer science at Korea University, advised by Prof.Heuiseok Lim.

    Computer Science From Baekseok University

    2011-2015

    I graduated from Baekseok University with a B.S. in Computer Science in Feb 2015.

    Work Experience

    Visiting PhD Student CLSP at Johns Hopkins University

    2019-2020
    Invited to JHU as a visiting graduate student at the Center for Language and Speech Processing (CLSP), advised by Prof.João Sedoc.
    Participated in three different projects as follows:
    • Created a dataset of conversations between people and state-of-the-art chatbots for WOCHAT+DBDC5 workshop
    • Collected crowd-sourced labels for the data and experiment several baseline models for evaluating generative dialogue systems.
    • Built COVID19 QA system (This effort leverages technologies developed under the support of organizations such as DARPA(the DEFT, LORELEI, AIDA, and KAIROS programs) and the JHU HLTCOE.)

    Research Completion From LearnLab at Carnegie Mellon University

    2015
    Responsibility :
    • Participated in track ”CSCL(Computer Supported Collaborative Learning)”, advised by Prof.Carolyn Rosè.
    • Developed the final project based on Google search aided system for education.

    Honors & Awards

    Best Paper Award (2020), Korea University

    Naver PhD fellowship Award (2019), Naver corporation

    Best Paper Award (2018), The Korean Association of Computer Education

    Best Paper Award (2018), The Korean Society of Fashion Business

    Best Paper Award (2018), The Korean Society of Fashion Business

    Best Paper Award (2016), The Korean Association of Computer Education

    Information Technology Master Scholarship (2013), KT corporation

    Wrap - A campanion plugin

    Wrap is a clean and elegant Multipurpose Landing Page Template. It will fit perfectly for Startup, Web App or any type of Web Services. It has 4 background styles with 6 homepage styles. 6 pre-defined color scheme. All variations are organized separately so you can use / customize the template very easily.

    It is a clean and elegant Multipurpose Landing Page Template. It will fit perfectly for Startup, Web App or any type of Web Services. It has 4 background styles with 6 homepage styles. 6 pre-defined color scheme. All variations are organized separately so you can use / customize the template very easily.

    • php
    • html
    • css
    • php
    • wordpress
    • React
    • Javascript
    Live Demo

    All variations are organized separately so you can use / customize the template very easily.

    All variations are organized separately so you can use / customize the template very easily.