Organization‎ > ‎Program‎ > ‎


18th (Mon)

09:00 - 09:10  |


Key-Sun Choi

09:10 - 10:10  |

Talk-1: Multi-source multi-strategical machine reading for KB development

Key-Sun Choi

10:10 - 10:30  |

Coffee Break

10:30 - 11:30  |

Talk-2: Introduction to and update to the LODQA project, and its harmonization to OKBQA

Jin-Dong Kim

11:30 - 12:30  |

Talk-3: Natural logic inferences


Christina Unger

12:30 - 14:00  |


14:00 - 15:00  |

Talk-4: Different semantic perspectives for hybrid question answering systems

André Freitas

15:00 - 15:10  |


Key-Sun Choi

15:10 - 15:30  |

Coffee Break

Talk-1: "Multi-source multi-strategical machine reading for KB development" (Key-Sun Choi)
A text has many shapes inside like sentences, itemized statements, tags, tables, etc. Machine reading strategy is also designed for each shape of text. This talk will introduce knowledge acquisition from sentences, itemized statements, and categories. Particularly, it is for Korean Wikipedia text for DBpedia style knowledge.

Talk-2: "Introduction to and update to the LODQA project, and its harmonization to OKBQA" (Jin-Dong Kim)
LODQA (Linked Open Data Question-Answering) is an open source project to develop an easily adaptable question-answering solution over linked open data. The system is highly modularized and designed to use generic solutions as much as possible avoiding optimization to specific applications, to maintain its applicability to various cases. Particularly, current implementation is focused on maximizing sensitivity of finding answers. The talk will include generation introduction, recent changes, and adaptation for OKBQA.

Talk-3: "Natural logic inferences" (Christina Unger)
An important part of understanding natural language is to be able to draw inferences from what is explicitly expressed. This talk will give an introduction to the field of Natural Logic, an approach to logical inferences that operates over natural language structures instead of formulas from a logical calculus. We will show how knowledge bases can be exploited for such inferences and how the results can, in turn, be applied for question answering and knowledge extraction.

Talk-4: "Different semantic perspectives for hybrid question answering systems" (André Freitas)
Question Answering systems define one of the most complex tasks in computational semantics. The intrinsic complexity of the QA task allows researchers of QA systems to investigate and explore different perspectives of semantics. However, this complexity also induces a bias towards a systems perspective, where researchers are alienated from a deeper reasoning on the semantic principles that are in place within the different components of the system. In this talk we will explore the semantic challenges, principles and perspectives behind the components of QA systems, aiming at providing a principled map and overview on the contribution of each component within the QA semantic interpretation goal.