Our paper 'Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach' (authors: Changgeon Ko, Jisu Shin, Hoyun Song, Jeong yeon Seo, and Jong C. Park) has been accepted at the SolaR workshop of NeurIPS 2024. Also, another paper 'PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling' (authors: Junmyeong Lee, Eui Jun Hwang, Sukmin Cho, and Jong C. Park) has been accepted at the SSL workshop of NeurIPS 2024. Congratulations!

Our papers have been accepted to EMNLP 2024! Our papers 'Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations' (authors: Sukmin Cho, Soyeong Jeong, Jeong yeon Seo, Taeho Hwang, and Jong C. Park) and 'Towards Effective Counter-Responses: Aligning Human Preferences with Strategies to Combat Online Trolling' (authors: Huije Lee, Hoyun Song, Jisu Shin, Sukmin Cho, SeungYoon Han, and Jong C. Park) have been accepted as findings of EMNLP 2024. Congratulations!

Our paper 'Ask LLMs Directly, "What shapes your bias?": Measuring Social Bias in Large Language Models' (authors: Jisu Shin, Hoyun Song, Huije Lee, Soyeong Jeong, and Jong C. Park) has been accepted as findings of ACL 2024! Also, another paper 'DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation' (authors: Taeho Hwang, Soyeong Jeong, Sukmin Cho, SeungYoon Han, and Jong C. Park) has been accepted at the KnowledgeNLP workshop of ACL 2024. Congratulations!

Our paper "Preprocessing Mediapipe Keypoints with Keypoint Reconstruction and Anchors for Isolated Sign Language Recognition" (authors: KyungGeun Roh, Huije Lee, Eui Jun Hwang, Sukmin Cho, and Jong C. Park) has been accepted at 11th Workshop on the Representation and Processing of Sign Languages:Evaluation of Sign Language Resources at LREC-COLING 2024. Congratulations to KyungGeun and all the authors!

Our paper "Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity" (authors: Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C. Park) has been accepted to NAACL 2024! Congratulations!

Our paper "A Gloss-free Sign Language Production with Discrete Representation" (authors: Eui Jun Hwang, Huije Lee, and Jong C. Park) has been accepted to FG 2024! Congratulations!

Three papers have been accepted in the EMNLP 2023 Conference. The titles of publications can be found in our Publication page. Congratulations to the authors!

Prof. Park gave a keynote speech titled "Human-Centric Natural Language Processing" at the Conference on Empirical Methods in Natural Language Processing (EMNLP 2023). The lecture video can be accessed by this link: https://underline.io/lecture/91320-human-centric-natural-language-processing-video

Professor Park serves as General Chair of IJCNLP-AACL 2023, the 17th International Joint Conference on Natural Language Processsing (IJCNLP) and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL), which is being held in Nusa Dua, Bali, Indonesia, during November 1-4, 2023.

SeungYoon Han joined our lab for the master's course starting from this semester (Fall 2023). Welcome!

Congratulations to Fitsum Gaim, Wonsuk Yang, Hancheol Park, and Prof. Jong C. Park on receiving the Outstanding Paper Award at the Association for Computational Linguistics (ACL) 2023! Their paper, entitled 'Question-Answering in a Low-resourced Language: Benchmark Dataset and Models for Tigrinya,' introduced the TiQuAD dataset, which is the first-ever Question-Answering Dataset for Tigrinya. They deserve big congratulations for their hard work and achievement, and this is a huge honor for our lab.

Our papers have been accepted in the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023). You can find the titles in the publication section. Great news for the first authors, co-authors, and all the lab members!

Our paper "Leveraging Large Language Models with Vocabulary Sharing for Sign Language Translation" (authors: Huije Lee, Jung-Ho Kim, Eui Jun Hwang, Jaewoo Kim, and Jong C. Park) has been accepted in the SLTAT workshop at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023)!

Our paper "Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement" (authors: Soyeong Jeong, Jinheon Baek, Sung Ju Hwang and Jong C. Park) has been accepted in the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023), congratulations!

Taeho Hwang joined our lab for the master's course starting from this semester (Spring 2023). Welcome!

Our papers "Sign Language Production With Avatar Layering: A Critical Use Case over Rare Words" (authors: Jung-Ho Kim, Eui Jun Hwang, Sukmin Cho, Du Hui Lee, and Jong C. Park), "GeezSwitch: Language Identification in Typologically Related Low-resourced East African Languages" (authors: Fitsum Gaim, Wonsuk Yang, and Jong C. Park), and "ELF22: A Context-based Counter-Trolling Dataset to Combat Internet Trolls" (authors: Huije Lee, Young Ju NA, Hoyun Song, Jisu Shin, and Jong C. Park) have been accepted in the Proceedings of the 13th Language Resources and Evaluation Conference (LREC 2022), congratulations!

Our paper "Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation" (authors: Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C. Park) has been accepted in the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), congratulations!

Our paper "Non-Autoregressive Sign Language Production with Gaussian Space" (authors: Eui Jun Hwang, Jung-Ho Kim, and Jong C. Park) has been accepted in the 32nd British Machine Vision Conference (BMVC 2021), congratulations!

Sukmin joined our lab for the master's course starting from this semester. Welcome!

We renewed our lab bulletin board. Thanks for sharing decoration ideas, it looks great!

ChaeHun and Jisu joined our lab for the PhD's course and the master's course starting from this semester. Welcome!

Soo Hyun Ryu did research assistant from our lab and performed all her duties conscientiously. We wish her the best of luck in her future career.

Our lab attended the 2nd K-GLOBAL briefing seminar on technology transfer held in the web on July 15, 2020. Prof. Park gave a presentation for our project titled "A system and method for communication training program over virtual reality and continued feedback via mobile device".

Euijun and Soyeong joined our lab for the PhD's course and the master's course starting from this semester. Welcome!

Our papers "Implementation of Word Embeddings in Predicting Meaning Dominance of Homonyms" (author: Soo Hyun Ryu and Jong C. Park) and "The effect of statistical information on the acceptability of generics" (author: Soo Hyun Ryu, Wonsuk Yang, Jong C. Park) have been accepted at the 2020 Annual Conference of the Korean Society for Cognitive and Biological Psychology.

Our paper "Unsupervised inference of implicit biomedical events using context triggers" (author: Jin-Woo Chung, Wonsuk Yang, and Jong C. Park) has been accepted in the BMC Bioinformatics, 2020 (IF 2.511).

Our paper "TEA: The Effect of the Textual Entailment on the Acceptability Changes" (author: Junseop Ji, Wonsuk Yang, and Jong C. Park) has been accepted at the Human-Computer Interaction Korea 2020 (HCI 2020).

Most members of NLP*CL lab attended the 2019 SW StarLab Future SW Technology Forum held in the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea on November 22, 2019. Prof. Park hosted and held the 2019 SW StarLab Future SW Technology Forum successfully.

Wonsuk, Seungwon, ChaeHun, and Prof. Park attended the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019) held in Hong Kong SAR, on November 2–7, 2019. Wonsuk gave an oral presentation for the long paper titled "Nonsense!: Quality Control via Two-Step Reason Selection for Annotating Local Acceptability and Related Attributes in News Editorials". Seungwon gave an oral presentation for the paper titled "Computer Assisted Annotation of Tension Development in TED Talks through Crowdsourcing" at the 1st Workshop on AnnoNLP. ChaeHun gave an oral presentation for the paper titled "Generating Sentential Arguments from Diverse Perspectives on Controversial Topic" at the NLP4IF 2019 workshop.

Our papers "Computer Assisted Annotation of Tension Development in TED Talks through Crowdsourcing" (authored by Seungwon Yoon, Wonsuk Yang, and Jong C. Park) and "Generating Sentential Arguments from Diverse Perspectives on Controversial Topic" (authored by ChaeHun Park, Wonsuk Yang, and Jong C. Park) have been accepted as long papers at the 1st Workshop on Aggregating and analysing crowdsourced annotations for NLP (AnnoNLP) (1st AnnoNLP) and the 2nd Workshop on NLP for Internet Freedom (NLP4IF): Censorship, Disinformation, and Propaganda (NLP4IF 2019), respectively.

Cholé Paris did her summer research internship from our lab and performed all her duties conscientiously. We wish her the best of luck in her future career.

Our paper "Nonsense!: Quality Control via Two-Step Reason Selection for Annotating Local Acceptability and Related Attributes in News Editorials" (authored by Wonsuk Yang, Seungwon Yoon, Ada Carpenter, and Prof. Park) has been accepted as a long paper at the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019).

Minseo Kim did his summer research program from our lab and performed all his duties conscientiously. We wish him the best of luck in his future career.

We renewed our lab bulletin board. Thanks for sharing decoration ideas, it looks great!

Our paper "A Corpus of Sentence-level Annotations of Local Acceptability with Reasons" (authored by Wonsuk Yang, Jung-Ho Kim, Seungwon Yoon, Chaehun Park, and Prof. Park) has been accepted as a long paper at the 33rd Pacific Asia Conference on Language, Information and Computation (PACLIC 33).

The NLP*CL Lab held its "2019 Homecoming Day" on 22nd of June.
Professor, alumni and current students gathered together to have a good time.

We are delighted to announce that Soo Hyun Ryu and Cholé Paris joined our lab as a researcher and an intern. Welcome!

Our paper "Automatic Scoring of Semantic Fluency" (author: Najoung Kim, Jung-Ho Kim, Maria K. Wolters, Sarah E. MacPherson, and Jong C. Park) has been published in the Frontiers in Psychology (SSCI, impact factor 2.089) on 16th May, 2019.

Junseop joined our lab for the master's course starting this semester. Welcome!

Wonsuk, Fitsum, Hoyun, Huije, Seungwon and ChaeHun attended the KSC (Korea Software Congress) 2018 held in Pyeongchang, Korea on December 19-21, 2018. Fitsum gave an oral presentation for the paper titled "Neural Grammatical Error Correction by Simulating the Human Learner and the Human Proofreader". Huije gave an oral presentation for the paper titled "Mitigating Stereotypes in Word Embedding through Sentiment Modulation".

Jinseon and Hoyun attended the 32nd Pacific Asia Conference on Language, Information and Computation (PACLIC 32) held in Hong Kong, on December 1–3, 2018. Hoyun gave an oral presentation for the paper titled "Feature Attention Network: Interpretable Depression Detection from Social Media".

Ada Carpenter joined our lab for the internship. Welcome!

Huije, Seungwon and ChaeHun attended the HCLT (Human & Cognitive Language Technology) Korea 2018 held in Seoul, Korea on October 12-13, 2018. Seungwon gave an oral presentation for the paper titled "Automatic Tension Recognition from Lecture Show Transcript". ChaeHun gave an oral presentation for the paper titled "Extracting Supporting Evidence with High Precision via Bi-LSTM Network".

Our papers "Automatic Tension Recognition from Lecture Show Transcripts" (authored by Seungwon Yoon, Wonsuk Yang, and Prof. Park) and "Extracting Supporting Evidence with High Precision via Bi-LSTM Network" (authored by ChaeHun Park, Wonsuk Yang, and Prof. Park) have been accepted as a long paper at the 30th Annual Conference on Human & Cognitive Language Technology (HCLT 2018).

Most members of NLP*CL lab attended the 2018 SW StarLab Future SW Technology Forum held in Seoul National University, Seoul, Korea on August 24, 2018. Prof. Park gave a presentation for our StarLab project titled "How much do I trust what you say? What evidence do I need?".

The NLP*CL Lab held its "2018 Homecoming Day" on 2nd of June.
Professor, alumni and current students gathered together to have a good time.

The Korean Ministry of Science and ICT and IITP selected our lab as a SW Star Lab of intelligent software on April 20, 2018. The selected lab will receive project funding of up to 300 million won per year for up to eight years and is encouraged to develop a world-class research agenda through open software.

Our lab will work on the development of software for automatically predicting the credibility distribution of given documents and dialogues, consisting of five modules: data collection, automatic collection of evidence, credibility enhancement, credibility distribution prediction, and linguistic analysis.

This year, a total of five laboratories have been selected in four universities: Seoul National University, POSTECH, Chung Ang University, and KAIST. There are two laboratories in the field of intelligent software including our lab.

Seungwon and ChaeHun joined our lab as master's students starting from this semester. Welcome!

Huije and Hoyun attended the HCI (Human-Computer Interaction) Korea 2018 held in Jeongseon, Korea on January 31-February 2, 2018. Huije gave an oral presentation for the paper titled "Detection of Non-Standard Meaning Usage with Word Embedding".

Jung-Ho, Wonsuk, Hoyun and Huije attended the Korea Software Congress 2017 held in Busan, Korea on December 20-22, 2017. Hoyun gave an oral presentation for the paper titled "Predicting Symptoms of Depression for Social Media Users via Linguistic Patterns" and Jung-Ho, Youngjin (CGV Lab.), and Wonsuk attended SW/Demo Contest as a team named 'NLPCL * CGV' and won the best (최우수) demo award. Congratulations!

Jinseon, Jin-Woo, and Prof. Park attended the 8th International Joint Conference on Natural Language Processing (IJCNLP 2017) held in Taipei, Taiwan, on November 27–December 1, 2017. Jinseon gave an oral presentation for the long paper titled "Extraction of Gene-Environment Interaction from the Biomedical Literature".

Jin-Woo won the NAVER PhD fellowship award given by NAVER Corporation. Congratulation!

NAVER PhD fellowship award is given to PhD students in computer science who have published top-tier conference papers and journal articles. Jin-Woo has done work on spatial information inference from text and presented research results to IJCAI 2017.

Our paper "Extraction of Gene-Environment Interaction from the Biomedical Literature" (authored by Jinseon You, Jin-Woo Chung, Wonsuk Yang, and Prof. Park) has been accepted as a long paper at the 8th International Joint Conference on Natural Language Processing (IJCNLP 2017).

Jin-Woo, Wonsuk, and Prof. Park attended the 26th International Joint Conference on Artificial Intelligence (IJCAI-17) held in Melbourne, Australia on August 19-25, 2017. Jin-Woo gave an oral presentation for the main track paper titled "Inferring Implicit Event Locations from Context with Distributional Similarities".

Fitsum Gaim will start his PhD program in School of Computing and join our lab this Fall. He will receive his master's degree in Global Information & Telecommunication Technology Program (ITTP) at KAIST. Welcome!

Our paper "Inferring non-stated event locations from context using distributional similarities" (authored by Jin-Woo Chung, Wonsuk Yang, Jinseon You, and Prof. Park) has been accepted as a main track paper at the 26th International Joint Conference on Artificial Intelligence (IJCAI 2017).

Hoyun and Huije joined our lab for the master's course starting this semester. Welcome!

The 12th Korea-Singapore Joint Workshop on Bioinformatics and Natural Language Processing was held in KAIST and Gyeryongsan Natural History Museum, Daejeon, Korea on Sept. 22-23, 2016. We had five invited presentations given by Prof. Limsoon Wong (NUS, Singapore), Prof. Kwang-Hyun Cho (KAIST, Korea), Dr. See-Kiong Ng (I2R, Singapore), Dr. Jie Zheng (NTU, Singapore), and Dr. Wei Lu (SUTD, Singapore).

Jung-Ho and Najoung attended Interspeech 2016 held in California on Sept. 8-12, 2016.

Jin-Woo and Prof. Park attended the 15th European Conference on Computational Biology (ECCB 2016) held in Hague on Sept. 4-7, 2016.

Hancheol, Jinseon, Jimin, and Wonsuk attended the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016) held in Berlin on Aug. 8-11, 2016.

Prof. Park gave an invited talk titled "Automatic Sign Language Generation" in the welfare technology seminar hosted by Graduate School of Science and Technology Policy at KAIST (KAIST STP) on July 4, 2016.

Jimin, Hancheol, and Jin-Woo attended the Korea Computer Congress 2016 held in Jeju Internatioanl Convention Center on June 29 - July 1, 2016. Hancheol gave an oral presentation for the paper titled "Addressing Low-Resource Problems in Statistical Machine Translation of Sign Language" and won the best paper award. Jimin gave a poster presentation for the paper titled "Classification of Relations between Biological Entities using Word Vectors".

Prof. Park gave an invited talk titled "Language processing through the collaboration with field experts" at the 2016 Spring conference of the Language Research Institute of Hankuk University of Foreign Studies on May 27, 2016.

The 3rd Korea-Europe Workshop on Biomedical Informatics and Natural Language Processing was held in KAIST and Hotel DongHak SanJang on February 16-18, 2016. We had two invited presentations given by Dr. Sarah MacPherson and Dr. Maria Wolters from the University of Edinburgh.

We attended the HCI Korea 2016 conference held in High1 Resort, Gangwon on Jan. 27-29, 2016. Najoung gave an oral presentation for the paper titled "A Morphological Approach to the Longitudinal Detection of Dementia".

Jinseon attended the KIISE winter Conference (한국정보과학회 동계학술발표회) held at Phoenix Park, on December 17-19, 2015. Jinseon gave a poster presentation for the paper titled "Biomedical Event Extraction and Management in Big-scale Biomedical Literature"

Jin-Woo, Jinseon, and Prof. Park attended the 29th Pacific Asia Conference on Language, Information and Computing (PACLIC 29) held in Changhai on Oct. 30-Nov. 1, 2015. Jin-Woo gave an oral presentation for the paper titled "Corpus annotation with a linguistic analysis of the associations between event mentions and spatial expressions".

Dr. Jin, Jinseon, and Prof. Park attended the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2015) held in Beijing on July 27-30, 2015. Dr. Jin gave an oral presentation for the paper titled "CoMAGD: Annotation of Gene-Depression Relations" at the BioNLP 2015 workshop.

Umang Sehgal did his internship from our lab and performed all his duties conscientiously. We wish him the best of luck in his future career.

Jinseon, Jin-Woo, and Dr. Jin attended the Korea Computer Congress (KCC) 2015 held in Jeju on June 24-26, 2015. Jinseon gave an oral presentation for the paper titled "Identification of Depression-Gene Associations from Biomedical Literature".

지난 5월 30일 토요일에 연구실 홈커밍데이 행사가 있었습니다. 교수님과 졸업생 선배님들 및 재학생 분들이 한 자리에 모여서 유익한 시간을 가졌습니다.

Dr. Maria Wolters from the University of Edinburgh visited KAIST on 24th April, 2015. We had a discussion about scoring methods for the category fluency test.

Sungyup and Jimin joined our lab for the master's course starting this semester. Welcome!

The 2nd Korea-Europe Workshop on Biomedical Informatics and Natural Language Processing was held in the KI building, KAIST on February 27, 2015. We had two invited presentations given by Dr. Sarah MacPherson and Dr. Maria Wolters from the University of Edinburgh, and two technical presentations given by Dr. Hee-Jin Lee from KAIST and Dr. Cheol Han from the Korea University. We also had work-in-progress presentations given by four students from our group and the CGV group.

We are delighted to announce that Dr. Rize Jin joined our lab as a post-doctoral researcher. Please welcome Dr. Rize Jin.

Our system OncoSearch was introduced as one of the top 10 research results of KAIST this year in the 2014 December issue of the KAISTAR webzine. (link: http://kaistar.e-eyagi.com/sub02/articles/view/tableid/board9/id/4750)

Jung-Ho, Jinseon, and Jin-Woo attended the KIISE winter Conference (한국정보과학회 동계학술발표회) held at Phoenix Park, on December 18-20, 2014. Jung-Ho gave a poster presentation for the paper titled "Construction of a Korean-to-KSL Parallel Corpus by Effective Motion Capture of Hand Shapes".

We had a pre-Christmas party with CS579 and CS790 students on December 17th, 2014.

Our research was introduced in the 400th issue of the KAIST newspaper as one of the most outstanding research results of KAIST this year.

Title: 2014년, KAIST를 빛낸 연구성과를 소개합니다
Link: http://times.kaist.ac.kr/news/articleView.html?idxno=2992

Jung-Ho, Jinseon, and Prof. Park attended the 28th Pacific Asia Conference on Language, Information and Computing (PACLIC28) held in Phuket, Thailand on December 12-14, 2014.

Dr. Maria Wolters from the University of Edinburgh visited KAIST on 7th December, 2014 and stayed in our laboratory for 3 days. We had several discussions about new, refined analyses that have been conducted on Korean and UK CFT data, including a data collection method and integration of CFT work with existing work of our group.

Jung-Ho won the best paper award for the paper titled "An Effective Construction of a Korean-to-KSL Parallel Corpus" at the 26th Annual Conference on Human and Cognitive Language Technology (HCLT 2014).

Jinseon joined our lab for the master's course starting this semester.

Jin-Woo won the Best TA award for his teaching assistant activities in CS372 (Natural Language Processing with Python; Spring semester, 2014).

우수연구성과를 통해 연구자들의 연구 활동을 소개하는 한국연구재단 웹진의 '4인4색' 코너에 우리 연구실이 소개되었습니다.
링크: http://webzine.nrf.re.kr/nrf_1408/know/know_2_4.php

Jung-Ho, Jinsun, Jin-Woo and Prof. Park attended the 25th International Conference on Computational Linguistics (COLING 2014) held in Dublin, Ireland on August 24-29, 2014.

우리 연구실에서 발표한 OncoSearch가 국립암센터에서 발간하는 웹진 “암연구동향: 국립암센터가 제공하는 국내외 최신 암연구정보”의 2014년도 7월호에 국내 우수 연구성과로 소개되었습니다. (웹사이트 링크)

Our research was introduced in the June issue of Science & Creativity, a Korean monthly science magazine published by the Korea Foundation for the Advancement of Science and Creativity (KOFAC). See the article here. The full issue is available at http://www.kofac.re.kr/ebook/monthly/2014/201406.pdf.

Our system OncoSearch (paper: "OncoSearch: Cancer Gene Search Engine with Literature Evidence") was covered by the media in Korea on 23rd May, 2014. OncoSearch is a text mining search engine that searches Medline abstracts for sentences describing gene expression changes in cancers. The research results were published in the online version of Nucleic Acids Research, on 9th May, 2014. OncoSearch is available through http://oncosearch.biopathway.org

Sources
- Ministry of Science, ICT and Future Planning (미래창조과학부): "암관련 유전자 검색 엔진 개발"
- Health Korea News: "암 관련 유전자 빠르고 정확히 찾는다"
- Dong-A Science: "7500개 암 유전자 한번에 촤르륵 검색"
- Yonhapnews: "암 유전자 '검색엔진' 개발…암 연구 수월해질듯"
- Electronic Times: "암 관련 유전자 정보 검색 기술 개발"
- YTN: "암 관련 유전자 전용 검색 엔진 개발" (YouTube)

Our paper "OncoSearch: Cancer Gene Search Engine with Literature Evidence" (author: Hee-Jin Lee, Tien Cuong Dang, Hyunju Lee, and Jong C. Park) was published in the Nucleic Acids Research (NAR, impact factor 8.27) on 9th May, 2014.

Seung-Cheol, Gang-Jae and Prof. Park visited the University of Edinburgh on January 27th, 2014. They stayed at the School of Informatics for 7 days and had meetings with Dr. Maria Wolters and Dr. Sarah MacPherson for joint research on computational approaches to diagnosis of language impairments.

We had a pre-Christmas party with CGV lab members and CS579 and CS790 students on December 20th, 2013!

The Korea-Europe Workshop on Biomedical Informatics and Natural Language Processing was successfully held on 16th December, 2013. We had three invited talks given by Dr. Goran Nenadic from the University of Manchester, UK, Dr. Fabio Rinaldi from the University of Zurich, Switzerland, and Prof. Hyunju Lee from GIST, Korea. We also had three additional presentations given by our lab members, Dr. Hye-Jin Min, Hee-Jin Lee, Seung-Cheol Baek, and Jin-Woo Chung.

Date: 2013.12.16(Mon.) 15:00
Venue: Lecture Room Blue (B301), KI Bldg.
Host: Jong C. Park

Speaker:
Goran Nenadic, University of Manchester, UK

Title:
Contextualising biomedical text mining: from facts to contradictions

Abstract:
To date, progress in biomedical text mining research has primarily focused on entity recognition (locating mentions of species, genes, diseases, clinical findings, etc.) and the extraction of relationships (e.g. between genes/proteins, between diseases and genes etc.). Most of the extracted information is considered as facts and is not placed in the context that delineated the research reporting such facts. In this talk I will overview our efforts to contextualise the results of biomedical text mining by extracting the associated features that charcterise the extracted facts. These include not only negation and speculation, but also associated species, anatomical locations, diseases, aging, etc. I will present several systems and automatically extracted knowledge bases that span themes from biology, bioinformatics and clinical practice.

Speaker Bio:
Dr Goran Nenadic is a Senior Lecturer in the School of Computer Science, University of Manchester, and is a group leader in the Manchester Interdisciplinary BioCenter (MIB). Previously, he was lecturer in the School of Informatics, a post-doctoral research fellow in the same School (former Department of Computation, UMIST), a research fellow at the NLP group, University of Salford, UK, a teaching assistant at the Faculty of Mathematics, University of Belgrade and a visiting teaching assistant in Computational linguistics at the Faculty of Philology, University of Belgrade. Goran has been working in the area of text mining and natural language processing since 1993. His research interests include terminology extraction, acquisition, classification and clustering (mainly in the domain of life sciences), relationship extraction, as well as interoperable architectures for text mining services and digital corpora encoding frameworks. Currently, Goran Nenadic is a principal investigator on a BBSRC project that aims at extraction of associations among various types of entities from the biological literature (bio-MITA - Mining Term Associations from Literature to Support Knowledge Discovery in Biology).

Seung-Cheol and Prof. Park attended the 6th International Joint Conference on Natural Language Processing (IJCNLP 2013) held in Nagoya, Japan, on October 14-18, 2013. Seung-Cheol gave an oral presentation for the paper titled "Parsing Dependency Paths to Identify Event-Argument Relations" co-authored by Prof. Park. Prof. Park has served as a co-chair of the program committee of this conference.

Jin-Woo attended the 22nd IEEE International Symposium on Robot and Human Interactive Communication (IEEE RO-MAN 2013, http://www.ro-man2013.org) in Gyeongju, Korea from August 26 to 29, 2013. He gave an oral presentation for a paper titled "Speaker-TTS Voice Mapping towards Natural and Characteristic Robot Storytelling". (author: Hye-Jin Min, Sang-Chae Kim, Joon-Yeob Kim, Jin-Woo Chung, and Jong C. Park)

Jin-Woo and Prof. Park attended the 3rd International Conference on Web Intelligence, Semantics, and Mining (WIMS) held in Spain, Madrid, on June 12-14, 2013. Jin-Woo gave an oral presentation for the paper "Enhancing Readability of Web Documents by Text Augmentation for Deaf People" co-authored by Hye-Jin, Joonyeob and Prof. Park.

지난 6월 8일 토요일에 연구실 홈커밍데이 행사가 있었습니다. 교수님과 졸업생 선배님들 및 재학생 분들이 한 자리에 모여서 즐거운 시간을 가졌습니다.

We attended the HCI 2013 Conference Korea held in High1 Resort, Gangwon on Jan. 30-Feb. 1, 2013. Yong-Jae gave an oral presentation for the paper "Blog Corpus-based Clustering Scheme for Category Fluency Test (CFT) Data Clustering" (co-authored by Dr. Maria Wolters from the University of Edinburgh, Hee-Jin, and Prof. Park).

JoonYeob and Jin-Woo attended the KIISE Fall Conference (한국정보과학회 추계학술발표회) held in Chungnam National University, on November 23-24, 2012. JoonYeob gave a poster presentation for the paper "Analyzing and Mapping Expressions of Tense for Korean-Korean Sign Language Translation" (co-authored by Jin-Woo and Prof. Park).

Hye-Jin and Prof. Park attended the 26th Pacific Asia Conference on Language, Information, and Computation (PACLIC 26) held in Bali, Indonesia, on November 7-10, 2012. Hye-Jin gave an oral presentation for the paper "Product Name Classification for Product Instance Distinction".

We attended the HCLT 2012 conference (제24회 한글 및 한국어 정보처리 학술대회) held at the Korea Maritime Univ., Busan, on October 11-13, 2012. Hye-Jin gave an oral presentation for a paper titled "Automatic Speaker Identification in Fairytales towards Robot Storytelling" (로봇 동화 구연을 위한 동화 상 발화문의 화자 자동파악) co-authored by Sang-Chae and Prof. Park.

Seung-Choel and Prof. Park attended the 5th International Symposium on Semantic Mining in Biomedicine (SMBM) held in University of Zurich, Switzerland, on September 3-4, 2012. Seung-Choel gave an oral presentation for the paper "Use of Clue Word Annotations as the Silver-standard in Training Models for Biological Event Extraction".

Jin-Woo, Hye-Jin and Joon-Yeop attended the 14th Annual Conference on Korean Sign Language (제14회 한국수화학회 학술대회) held in Korean Nazarene University, Cheonan, on August 15th, 2012.

이용재 군이 Maria Wolters 박사님과의 공동 연구를 위해 BK21의 지원을 받아 8월 14일부터 29일까지 영국 University of Edinburgh로 출장을 다녀옵니다.

The 5th International Symposium on Semantic Mining in Biomedicine (SMBM) will be held at the Institute of Computational Linguistics, University of Zurich, Switzerland on 3rd-4th September, 2012.
(website: http://www.smbm.eu)

Prof. Mark Steedman, Prof. Bonnie Webber and Dr. Maria Wolters from the University of Edinburgh visited KAIST on July 16, 2012. Prof. Webber gave a Global lecture titled "Discourse in Language Technology" for CS students on July 17 and 19. Prof. Steedman and Dr. Wolters gave talks titled "Inducing Natural Language Grammars and Parsers from Data" and "Designing Reminder Systems for Older People - What is the Context?", respectively. We also had a good time in Jeonju Hanok Village on July 18 and Mt. Gyeryong on July 20. (see photos here)

Dr. Maria Wolters from the University of Edinburgh will give a talk at KAIST on July 16th as follows:

Title: Designing Reminder Systems for Older People - What is the Context?
Speaker: Dr. Maria Wolters, University of Edinburgh
Date: July 16 (Monday), 2012
Time: 1:00pm ~ 2:00pm
Place: Ahn Young-Kyung Seminar Room, CS Building (#4420, E3-1)
Host: Jong C. Park (park@cs.kaist.ac.kr)

Abstract: In the MultiMemoHome project, we aim to develop guidelines for designing acceptable and effective reminders for supporting older people who live in the community. An important part of the design is to consider the context in which reminders are delivered. Is the person who needs the reminders living alone or with family? How large is their social network? How close are they to other people who could help? What technology do they have in their home that could be used to display reminders? What sensory and cognitive impairments do they have that might preclude reminder use? We will look at those questions using data from the English Longitudinal Survey of Ageing, a large-scale study of thousands of older people in the UK. The talk will conclude with suggestions for relevant cross cultural comparisons.

Biography: Maria Wolters is a senior research fellow at the Centre for Speech Technology Research at the University of Edinburgh. The goal of her research is to improve the accessibility and functionality of voice-based interaction. She is also interested in the quantitative analyses of large quantities of language data and in the acoustic analysis of disordered speech.

She studied at the University of Bonn, where she attained an MSc in Computer Science in 1997 and a PhD in Communication Research and Phonetics in 2001. She went on to join the University of Newcastle and Queen Margaret University as a clinical phonetician, before moving to the University of Edinburgh in late 2004. She is currently a research fellow on the MATCH project.

Prof. Anoop Sarkar from Simon Fraser University visited KAIST and gave a talk titled "Four Methods for Morpheme-based Machine Translation" on July 2, 2012.

We attended the KCC 2012 conference (한국컴퓨터종합학술대회 2012) held in Jeju island on June 27-29, 2012. Yong-Jae gave a poster presentation for a paper titled "Towards Automatic Evaluation of Category Fluency Test Performance: Distinguishing Groups using Word Clustering" (자동 범주유창성검사 평가를 향하여: 단어 군집화를 활용한 그룹간 구별) co-authored by Dr. Maria Wolters from the University of Edinburgh, and Hee-Jin Lee. Sang-Chae gave another poster presentation for a paper titled "Age and Gender Prediction from Korean Tweets with Stylometric Analysis" (문체 분석을 활용한 한국어 트위터 사용자의 연령대 및 성별 예측).

Prof. Bonnie Webber from the University of Edinburgh will give a Global lecture at KAIST on July 17th and 19th as follows:

Title: Discourse in Language Technology
Speaker: Professor Bonnie Webber
Affiliation: School of Informatics, University of Edinburgh (UK)
Time:
- Lecture 1: July 17 (Tuesday), 2012, 2:00 PM ~ 5:00 PM
- Lecture 2: July 19 (Thursday), 2012, 2:00 PM ~ 5:00 PM
Place: Oh Sang-Su Seminar Room, CS Building (#4443, E3-1)
Host: Professor Jong C. Park (박종철 교수)

Lecture Description
The discourse properties of text have long been recognized as critical to Language Technology, and over the past 40 years, our understanding of and ability to exploit these properties have grown in many ways. The goal of these two lectures is to recount these developments, the technologies they employ, the applications they support, and the new challenges that each subsequent development has raised. The audience will thus be introduced to viable notions of discourse structure that have emerged over the past two decades, and how they are being used to improve the performance of systems for information extraction, summarization, essay analysis and grading, sentiment detection and opinion mining, and machine translation.

LECTURE 1:
■ Description of several complementary bases that organize and structure texts, along with a description of their different formal properties.
■ Description of state-of-the-art algorithms for recognizing the different forms of text structure, along with resources used by these algorithms for training and/or testing (or that will soon be available for these purposes).

LECTURE 2:
■ Description of applications of these algorithms in automated essay evaluation, summarization, information extraction, opinion mining and sentiment detection.
■ Description of current and future applications of discourse structure in machine translation (MT), or facilitated through MT.

The lectures draw from recent articles and monographs, including [Webber et al, 2012], [Webber and Joshi, 2012], and [Stede, 2011]. They do not assume detailed linguistic knowledge on the part of audience members, but they do assume that the audience will have had some exposure to text, even if only as bags of words or N-gram language models.

Biography

Fellow, American Association for Artificial Intelligence (AAAI)
Vice President, Association for Computational Linguistics (ACL), 1979
President, Association for Computational Linguistics (ACL), 1980
Co-chair (with Benjamin Kuipers), National Conference on Artificial Intelligence (AAAI-97), 1997

PhD: Harvard University (1978)

Bibliography
Manfred Stede (2011). Discourse Processing. Morgan and Claypool Publishers.

Bonnie Webber and Aravind Joshi (2012). Discourse Structure and Computation: Past, Present and Future.
Proc. ACL Workshop on Rediscovering 50 Years of Discoveries. Jeju Island, Korea.

Bonnie Webber, Markus Egg and Valia Kordoni (2012). Discourse Structure and Language Technology.
Natural Language Engineering, doi:10.1017/S1351324911000337.

Contact: Hye-Jin Min (hjmin@nlp.kaist.ac.kr , T. 7741)

Prof. Anoop Sarkar from Simon Fraser University will give a talk at KAIST on July 2nd as follows:

Title: Two Methods for Morpheme-based Machine Translation
Speaker: Professor Anoop Sarkar (joint work with Ann Clifton and Young-chan Kim)
Affiliation: School of Computing Science, Simon Fraser University, BC (Canada)
Time: July 2 (Monday), 2012, 2:00 PM ~ 3:00 PM
Place: Oh Sang-Su Seminar Room, CS Building (#4443, E3-1)
Host: Professor Jong C. Park (박종철 교수)

Abstract:
Statistical machine translation systems learn how to translate by training on large amounts of previously translated text. The machine learning models used typically assume that the unit of translation is pre-defined (defined by an observed word boundary). As a result, these methods tend to perform poorly when translating into languages like Finnish or Korean with very complex morphological systems with a large vocabulary.

This talk is about our ongoing work in the use of unsupervised morpheme segmentation methods for machine translation. We investigate four methods: a generative model for generating word forms during translation (factored translation), translation based on word segments (sub-word translation), probability models for generating word forms in the target language (morphology generation) and sub-word alignment models that infer morphemes that can improve alignment between source and target languages (sub-word alignment).

The first three were evaluated on English to Finnish and the last method on English to Korean translation.

We find that morphology aware translation models yield significantly more fluent translations compared to a state of the art word-based baseline. We perform linguistic analysis of the output to show that morpheme-aware translations are more fluent and we show improvements in automatic evaluation scores like BLEU.

Biography:
Anoop Sarkar is an Associate Professor in Computing Science at Simon Fraser University in British Columbia, Canada where he co-directs the Natural Language Laboratory (http://natlang.cs.sfu.ca). He received his Ph.D. from the Department of Computer and Information Sciences at the University of Pennsylvania under Prof. Aravind Joshi for his work on semi-supervised statistical parsing using tree-adjoining grammars. His favorite machine translation system is kriya, the hierarchical phrase-based system developed in his lab at SFU.

His research is focused on statistical parsing and machine translation (exploiting syntax or morphology, or both). His interests also include semi-supervised learning algorithms and stochastic grammars, in particular tree automata and tree-adjoining grammars.

http://www.cs.sfu.ca/~anoop

Contact: Hye-Jin Min (hjmin@nlp.kaist.ac.kr, T. 7741)

프론티어사업 지능로봇사업단 17차 기술교류워크샵이 2월 16, 17일 양일에 걸쳐 강원도 횡성 현대성우리조트에서 개최되었습니다. 8-1과제에 속하는 우리 연구실은 길상용, 김상채 학생이 참석하여 포스터 전시 및 발표를 하였습니다.

지난 1월 30일 학과 워크샵의 일정으로 박종철 교수님을 포함한 학과 교수님들께서 거제도의 삼성중공업을 방문하셨습니다.
(사진 크게 보기)

We attended the HCI 2012 Conference Korea held in Alpensia Resort on January 11-13, 2012. Yong-Jae and Sang-Chae presented a paper titled "Analyzing the Patterns of Switching and Clustering on CFT Data Using Hidden Markov Model" (authored by Yong-Jae Lee, Hee-Jin Lee, Maria Wolters, and Prof. Park) and a paper titled "Age Prediction from Korean Tweets with Style-Based Feature Analysis" (authored by Sang-Chae Kim and Prof. Park), respectively.

Prof. Park, Hee-Jin, and Seung-Cheol attended the 4th International Symposium on Languages in Biology and Medicine (LBM 2011) held at the Nanyang Technological University, Singapore on December 14th and 15th, 2011. Seung-Cheol gave a oral presentation for a paper titled "Analyzing Disagreements among ICD-9-CM Coders" (authored by Seung-Cheol Baek and Prof. Park) and Hee-Jin gave a poster presentation for a paper titled "Identifying Gene Expression Changes in Prostate Cancer Cells from the Literature" (authored by Hee-Jin Lee, Hyunju Lee, and Prof. Park).

Prof. Park gave a keynote speech titled "Automatic Conversion of Korean into Korean Sign Language Based on Combinatory Categorial Grammar" (결합범주문법을 이용한 한국어-수화 자동 변환) at the Joint Conference of the Modern Linguistic Society of Korea and the Korean Society for Language and Information (한국현대언어학회/언어정보학회 공동학술대회) at the Gongju National University of Education, on November 5, 2011.

Jin-Woo and Prof. Park attended the 2nd International Workshop on Sign Language Translation and Avatar Technology (SLTAT) and the 13th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) held in Dundee, UK on October 23-26, 2011. We presented two papers titled "Text Parsing for Sign Language Generation with Combinatory Categorial Grammar" (authored by Jin-Woo Chung and Prof. Park) and "Revisiting Concatenative Video Synthesis with Relaxed Constraints" (authored by Sangyong Gil and Prof. Park).

Hye-Jin attended the 5th International Joint Conference on Natural Language Processing (IJCNLP) held in Chiang Mai, Thailand, on November 8-13, 2011. She gave an oral presentation for a paper titled "Detecting and Blocking False Sentiment Propagation". See photos here.

프론티어사업 지능로봇사업단 16차 기술교류워크샵이 8월 24일부터 26일에 걸쳐 강원도 속초 파인리즈리조트에서 개최되었습니다. 이번 워크샵은 프론티어사업을 2년 남겨둔 시점에서 사업 종료 후 지능로봇 핵심원천기술들을 심화 발전시키기 위한 각 전문가들의 방향 제시와, 관계자와의 심도 깊은 토론을 위한 시간을 갖기 위한 목적으로 개최되었습니다. 8-1과제에 속하는 우리 연구실은 안승주, 길상용 학생이 참석하여 포스터 전시 및 발표를 하였습니다.

Yong-Jae and Sang-Chae attended KCC 2011 (한국컴퓨터종합학술대회) held in Gyeongju, Korea. Yong-Jae gave a poster presentation for a paper titled "Linguistic Analysis of Picture Description for Language Impairment Diagnosis" (언어 장애 진단을 위한 그림 설명글의 언어학적 특성 분석).

Prof. Park and Jin-Woo attended the International Conference on Web Intelligence, Mining and Semantics (WIMS'11) held in Sogndal, Norway on May 25-27, 2011. Jin-Woo gave an oral presentation for a paper titled "Improving Accessibility to Web Documents for the Aurally Challenged with Sign Language Animation".

Prof. Park visitied the University of Dundee on March 16, 2011 and gave an invited talk in the Research Seminar as follows:

Title: Quality of Life Technology for the Aurally Challenged and for the Aged
  
Abstract: 
Textual and spoken information is much widespread and ever expanding, but the consequent information divide is also quite serious, especially if we are challenged. We must also face it sooner or later as we age, though the precise nature of how well we adapt to this changing situation depends on the individual severity of declining brain functions with age, possibly coupled with symptoms such as dementia. In the first part of my seminar, I will introduce our on-going effort for the linguistic analysis and computational generation of sign language expressions for the aurally challenged. In the second part, I will describe our team effort to assess and help patients with declining brain functions by a synergistic and clinical integration of multiple-modal techniques, such as computational geometry, natural language processing, virtual reality and computer haptics, as members of a recently founded Systems Biomedical Research Centre, where I work as a group leader. Time permitting, I will prelude the second part of my talk briefly with descriptions of our past and on-going work on biomedical text mining and management.

Prof. Park and Hye-Jin attended the 6th International Conference on Human-Robot Interaction (HRI 2011) held in Lausanne, Switzerland. Hye-Jin presented a paper titled "Physical Push with a Socially Intelligent Robot: Make Your Wishes to 'Genie in the Lamp".

지능로봇사업단 OPEN LAB 및 15차 기술교류워크샵이 2월 23일과 24일 양일에 걸쳐 KIST 강릉분원에서 개최되었습니다. 이번 워크샵은 3단계 2차년도 상업화 단계에 들어선 각 연구과제별 우수 기술들을 소개함으로써 각 분야의 현안을 분석하고 국내 산학연 연구자들의 교류를 장려하기 위한 목적으로 개최되었습니다. 8-1과제에 속하는 우리 연구실에서는 이호준 박사님이 참석하였습니다.

올해 우리 연구실에서 이호준 선배님(박사)과 정진우 군(석사), 이용재 군(석사)이 2011학년도 졸업식에 참여하여 학위를 취득하였습니다. 모두 졸업을 축하드립니다!

We attended the HCI 2011 Conference Korea held in Alpensia Resort. SeungJoo gave an oral presentation for a paper titled "Korean Speech Synthesis for Automatic Fairy Tale Narration with Automatic Identification of Character Roles" (자동 동화 구연을 위한 등장 인물의 자동 역할 분류에 기반한 한국어 음성 합성 시스템) and Ho-Joon gave a poster presentation for a paper titled "Evaluation of Emotion Categories based on the Analysis of Emotion-Rich Fairy Tales" (동화에서 나타나는 감정 발화문의 특성 분석을 통한 감정 범주의 평가). Jin-Woo and Ho-Joon won a best paper award for a paper titled "Sentence Type Identification in Korean: Applications to Korean-Sign Language Translation and Korean Speech Synthesis" (한국어 문장 유형의 자동 분류: 한국어-수화 변환 및 한국어 음성 합성에의 응용).

지식경제부 프론티어사업 지능로봇사업단 제14차 로봇기술교류워크샵이 8월 25일 ~ 8월 27일 강원도 엘리시안 강촌에서 개최되었습니다. 이번 워크샵은 3단계 1차년도를 마감하면서 기술간 융복합의 가속화를 주제로 토의가 진행되었고, 각 세부과제 별 포스터 발표가 있었습니다. 우리 연구실에서는 민혜진 학생이 참석하였습니다. 8-1과제에 속하는 우리 연구실은 "다양한 감정/상황/의도 표현을위한 로봇표현 자동생성 기술"이란 제목의 포스터에 참여하였고, 1차년도 결과물인 "대조, 강조 표현 상의 핵심어휘 별 운율 정보 변화를 통한 감정음성 합성" 및 "문장유형의 자동 분류를 통한 문장 유형에 적합한 억양정보 합성"을 발표하였습니다.

오늘 수화연구자분들이 연구실을 방문하여 우리의 연구를 소개해드리는 자리가 있었습니다. 독일의 함부르크대학과 국립한국재활복지대학 및 여러 기관에서 수화를 언어학적으로 연구하시는 분들과 함께 유익한 시간을 가졌습니다. 이번 자리를 통해 우리의 연구를 알리고 앞으로의 연구 방향에 대한 많은 조언을 들을 수 있었습니다.

지난 20일에 평택의 국립한국재활복지대학에서 열린 제12회 한국수화학회 학술대회에 이호준 군과 정진우 군이 다녀왔습니다. 이번 학술대회는 '수화연구방법'이라는 공통의 주제 아래 발표가 이루어졌으며, 특히 수화 '자료'를 어떻게 수집할 것인지에 대한 많은 논의가 있었습니다. 특히 독일 함부르크대학 수화언어학과의 수화 유도(elicitation)자료 수집 방법과 수화코퍼스 구축 프로젝트는 앞으로 국내의 수화연구를 진행하는데 많은 도움이 될 수 있는 사례였습니다.

Prof. Park and Jin-Woo attended the 48th Annual Meeting of the Association for Computational Linguistics (ACL 2010) held in Uppsala, Sweden, on July 12-14, 2010. (http://acl2010.org/)
(photos)

지난 6월 5일 토요일에 연구실 홈커밍데이 행사가 있었습니다. 교수님과 졸업생 선배님들 및 재학생 분들이 한 자리에 모여서 즐거운 시간을 가졌습니다. 올해는 7분의 졸업생과 재학생 전원이 참석하였습니다. 수통골에서 점심식사를 하고 노은동 찻집에서 행사를 마무리하였습니다.
(photos)

Prof. Junichi Tsujii from the University of Tokyo visited KAIST on May 31st and gave a Global lecture (title: NLP-based Text Mining Techniques and their Applications) to KAIST students for five days.

Prof. Junichi Tsujii at the University of Tokyo will give a Global Lecture at KAIST as follows.

Title: NLP-based Text Mining Techniques and their Applications
Speaker: Junichi Tsujii
Date: May 31 - June 4, 2010 (1pm-4pm)
Location: Oh Sangsu Seminar Room
Host: Jong C. Park (park@cs.kaist.ac.kr)

[Course Description]
Text Mining has been considered as an essential technology in the future of biological research, which provides means by which scientists can cope with ever increasing amount of published papers in the domain. This course focuses on an emerging technological field, NLP-based Text Mining, which combines technologies such as natural language processing, ontology engineering, machine learning and distributed data bases. In particular, the course discusses how recent research results of deep parsing can be combined with machine learning for event recognition and relation mining in biology.

[Day 1] Challenges of Text Mining for Biology
[Day 2] Deep parsing and linguistic formalism
[Day 3] Empirical Approach to Meaning
[Day 4] Named Entity Recognition and Normalization
[Day 5] Event Recognition and Normalization

[Speaker's Bio]
Junichi Tsujii is a Professor of Computational Linguistics and Natural Language Processing of the University of Tokyo and Professor of Text Mining of the University of Manchester, UK. He has an MSc and a PhD from Department of Electrical Engineering, Kyoto University. He has been a permanent member of International Committee of Computational Linguistics (ICCL) from 1994. He was Vice-President (2005) and President (2006) of ACL (Association for Computational Linguistics), and President (2008) of AFNLP (Asian Federation of Natural Language Processing). He was awarded IBM Science Award in 1988, SEYMF Visiting professorship in 2000, Daiwa-Adrian Prize for the project jointly carried out by Dr.S.Ananiadou (University of Manchester, UK) in 2004, IBM Faculty Award in 2005, Achievement Award (Japan Society of Artificial Intelligence) in 2008, and 紫綬褒章 (the Japanese Government) in 2010.

The first CALBC ("Collaborative annotation of a large-scale biomedical corpus") workshop is to be held in 19/20 April 2010 at EBI (European Bioinformatics Institute, U.K.).

Location: European Bioinformatics Institute, Hinxton, Cambridge, U.K.
Date: 19/20 April 2010

The CALBC project is creating a broadly-scoped and diversely annotated corpus (several 100,000 Medline abstracts on immunology annotated with about a dozen semantic groups) by automatically integrating the annotations from different named entity recognition and concept identification systems. The result of the integration process will be a silver standard corpus (SSC).

The CALBC challenge, announced earlier to deal with biomedical named entity recognition (NER) and identification of entities, is now closed. At the CALBC workshop, participants of will discuss the outcome of the challenge. The CALBC project partner will explain in detail previous work on the corpus and will present the results from the challenge. Participants will present their work to meet the demands of the challenge.

The CALBC workshop offers the unique opportunity to learn more about this unusual approach to generate a large-scale annotated corpus. One highlight is the session about the exploitation of the scientific literature in Semantic Web applications. The workshop participants and members of the pharmaceutical industry will discuss how Semantic Web applications will profit from semantic enrichment of the scientific literature (as provided from the harmonised CALBC corpus).

지식경제부 프론티어사업 지능로봇사업단 제13차 로봇기술교류워크샵이 2월 24일 ~ 2월 26일 제주 휘닉스 아일랜드에서 개최되었습니다. 이번 워크샵은 3단계 1차년도를 마감하면서 기술간 융복합의 가속화를 주제로 토의가 진행되었고, 각 세부과제 별 포스터 발표가 있었습니다. 우리 연구실에서는 민혜진 학생이 참석하였습니다. 8-1과제에 속하는 우리 연구실은 "다양한 감정/상황/의도 표현을위한 로봇표현 자동생성 기술"이란 제목의 포스터에 참여하였고, 1차년도 결과물인 "대조, 강조 표현 상의 핵심어휘 별 운율 정보 변화를 통한 감정음성 합성" 및 "문장유형의 자동 분류를 통한 문장 유형에 적합한 억양정보 합성"을 발표하였습니다.

The 9th Korea-Singapore Joint Workshop on Bioinformatics and Natural Language Processing (http://ksw09.biopathway.org) was held in Oh Sang Soo Seminar Room at KAIST. The researchers from Singapore include Prof. Limsoon Wong (Professor and Head of Computer Science and Professor of Pathology at NUS) and Prof. Jung-Jae Kim, who received BSc, MS, and PhD all from CS Department at KAIST and recently joined the faculty of NTU in Singapore.

The 3rd International Symposium on Languages in Biology and Medicine (LBM) was held in Jeju island, Korea, November 8-10, 2009 (http://lbm2009.biopathway.org). LBM is an interdisciplinary forum that brings together researchers in biology, chemistry, medicine, public health and informatics to discuss and exploit cutting edge language technology. Language, in its many forms, is the universal means to represent, question, and convey knowledge. Likewise applied technologies such as information extraction, summarization, and translation are key technologies for advancing biomedical research and healthcare provision. The automation of all these solutions empowers our ability to discover new knowledge.

Dr. Jung-jae Kim has recently joined the faculty of Nanyang Technological University (NTU) in Singapore. He received his BSc, MS, and PhD in 1998, 2000, and 2006, respectively, at KAIST. He has worked as a post-doctoral researcher for the Text Mining group of European Bioinformatics Institute (EBI) from 2006 to 2009. He is currently exploring the usage of biomedical ontologies for text mining in order to facilitate the integration of text mining results into interoperable solutions for the biomedical community.

We attended the ACL-IJCNLP 2009 conference held in Singapore on August 2-7, 2009. Hye-Jin presented a paper titled "Toward finer-grained sentiment identification in product reviews through linguistic and ontological analyses". (photos)

2009년 7월 22일부터 24일까지 San Diego에서 있었던 HCI International 2009 학술대회에 참석하여 발표 및 학회 참관을 하고 돌아왔습니다.이번에 발표를 하면서 음성합성에 관련된 부분에 초점을 맞춰서 발표자료를 만들었었는데, 학회에 오셨던 분들은 이 외에도 감정 음성합성 시스템이 활용될 수 있는 분야나 evaluation 방법, evaluation 결과 등에도 많은 관심을 보이셨었습니다. 학회 발표 시간이 15분으로 짧기도 했었지만 이러한 관심사에 대해서 미리 알고 있었다면 좀 더 적극적인 발표가 될 수 있었을 것으로 생각되었습니다.이번 학회의 경우에는 많은 사람들이 데모를 위주로 발표를 하였는데, 학회 발표에서는 논문에 나와있는 내용을 자세하게 설명하기 보다는 사람들의 관심을 끌 수 있게 이러한 데모 시스템을 활용하는 것도 좋은 방법이라고 생각되었습니다. 또한 이러한 데모 시스템을 바탕으로하여 실제 생활에서 테스트를 하고 상용화 단계 바로 직전까지 완성을 목표로 많은 연구가 진행되는 것을 확인할 수 있었습니다.관심있게 본 내용은 노약자(특히 elderly)에 대한 연구가 눈에 띄게 많이 진행되고 있었다는 것과, 수화와 관련된 연구도 미국과 유럽 등지에서 많이 연구되고 있다는 것이었습니다. 실제 발표를 하시는 분 중에서도 수화로 의사소통을 하시는 분이 계셨었는데, 이 분의 발표 세션에는 수화 통역사가 계셔서 그 분의 수화 표현을 영어로 통역해 주셨었습니다.