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.

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

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

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

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

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

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

Ada Carpenter joined our lab for the internship. Welcome!

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

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).

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)

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. 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)

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).