no code implementations • GWC 2018 • Sangha Nam, Kijong Han, Eun-Kyung Kim, Key-Sun Choi
However, existing studies have a disadvantage in that they do not reflect the homograph in the word embedding used as an input of the relation extraction model.
no code implementations • PACLIC 2020 • Youngbin Noh, Kuntae Kim, Minho Lee, Cheolhun Heo, Yongbin Jeong, Yoosung Jeong, Younggyun Hahm, Taehwan Oh, Hyonsu Choe, Seokwon Park, Jin-Dong Kim, Key-Sun Choi
no code implementations • COLING 2020 • Jiseong Kim, Key-Sun Choi
We present a novel rule-based approach that finds positive and negative evidential paths in a knowledge graph for a given factual statement and calculates a truth score for the given statement by unsupervised ensemble of the found positive and negative evidential paths.
no code implementations • LREC 2020 • Younggyun Hahm, Youngbin Noh, Ji Yoon Han, Tae Hwan Oh, Hyonsu Choe, Hansaem Kim, Key-Sun Choi
Using current methods, the construction of multilingual resources in FrameNet is an expensive and complex task.
no code implementations • LREC 2020 • Sangha Nam, Minho Lee, Donghwan Kim, Kijong Han, Kuntae Kim, Sooji Yoon, Eun-Kyung Kim, Key-Sun Choi
Information extraction from unstructured texts plays a vital role in the field of natural language processing.
1 code implementation • COLING 2018 • Sangha Nam, Eun-Kyung Kim, Jiho Kim, Yoosung Jung, Kijong Han, Key-Sun Choi
The increased demand for structured knowledge has created considerable interest in knowledge extraction from natural language sentences.
no code implementations • COLING 2018 • Eun-Kyung Kim, Kijong Han, Jiho Kim, Key-Sun Choi
This demo deals with the problem of capturing omitted arguments in relation extraction given a proper knowledge base for entities of interest.
no code implementations • COLING 2016 • Jeong-uk Kim, Younggyun Hahm, Key-Sun Choi
FrameNet project has begun from Berkeley in 1997, and is now supported in several countries reflecting characteristics of each language.
no code implementations • WS 2016 • Jiseong Kim, Gyu-Hyeon Choi, Key-Sun Choi
Nowadays, a question answering (QA) system is used in various areas such a quiz show, personal assistant, home device, and so on.
no code implementations • COLING 2016 • Jiseong Kim, Gyu-Hyeon Choi, Jung-Uk Kim, Eun-Kyung Kim, Key-Sun Choi
Developing a question answering (QA) system is a task of implementing and integrating modules of different technologies and evaluating an integrated whole system, which inevitably goes with a collaboration among experts of different domains.
no code implementations • WS 2016 • Younggyun Hahm, Sangha Nam, Key-Sun Choi
Natural language questions are interpreted to a sequence of patterns to be matched with instances of patterns in a knowledge base (KB) for answering.
no code implementations • COLING 2016 • Eun-Kyung Kim, Key-Sun Choi
This demo presents MAGES (multilingual angle-integrated grouping-based entity summarization), an entity summarization system for a large knowledge base such as DBpedia based on a entity-group-bound ranking in a single integrated entity space across multiple language-specific editions.
no code implementations • WS 2016 • Sangha Nam, Gyu-Hyeon Choi, Younggyun Hahm, Key-Sun Choi
For this reason, we combine open information extraction with the reification for the full text extraction to preserve meaning of sentence in our knowledge graph.
no code implementations • LREC 2016 • Young-Seob Jeong, Won-Tae Joo, Hyun-Woo Do, Chae-Gyun Lim, Key-Sun Choi, Ho-Jin Choi
Before developing the system, it first necessary to define or design the structure of temporal information.
no code implementations • LREC 2014 • Younggyun Hahm, Jungyeul Park, Kyungtae Lim, Youngsik Kim, Dosam Hwang, Key-Sun Choi
In this paper, we propose a novel method to automatically build a named entity corpus based on the DBpedia ontology.
no code implementations • WS 2012 • YoungGyun Hahm, Kyungtae Lim, Jungyeul Park, Yongun Yoon, Key-Sun Choi