Pum-Mo Ryu

Open domain question answering using Wikipedia-based knowledge model

This paper describes the use of Wikipedia as a rich knowledge source for a question answering (QA) system. We suggest multiple answer matching modules based on different types of semi-structured knowledge sources of Wikipedia, including article content, infoboxes, article structure, category structure, and definitions. These semi-structured knowledge sources each have their unique strengths in finding answers for specific question types, such as infoboxes for factoid questions, category structure for list questions, and definitions for descriptive questions. The answers extracted from multiple modules are merged using an answer merging strategy that reflects the specialized nature of the answer matching modules. Through an experiment, our system showed promising results, with a precision of 87.1%, a recall of 52.7%, and an F-measure of 65.6%, all of which are much higher than the results of a simple text analysis based system.

Named entity recognition using a modified Pegasos algorithm

In this paper, we describe a named entity recognition using a modified Pegasos algorithm for structural SVMs. We show the modified Pegasos algorithm significantly outperformed CRFs and the training time for the modified Pegasos algorithm is reduced 17-26 times compared to CRFs.

Paraphrase generation based on lexical knowledge and features for a natural language question answering system

A question answering (QA) system constructs its answers automatically by querying a structured database known as a knowledgebase or an unstructured collection of documents and a set of questions. Paraphrase approaches are widely used to solve paraphrastic problems in natural language QA systems. In machine-learning-based Korean paraphrase, the system requires a large-scale mono/bi-lingual corpus. However, thus far, a well-structured corpus is lack, and it is difficult to get alignment data between Korean and English without noise for entailment. This paper creates paraphrase sentences using synonym knowledge and the various features of full morphemes. The results here demonstrate that the paraphrase quality can be improved by the following features: the morpheme type, the dependencies, and the semantic arguments. The feature of the semantic role labeling (SRL) results can be of assistance when attempting to solve instances of word sense disambiguation (WSD) for lexical replacement in Korean.

An Effective Document Classification System Based on Concept Probability Vector

This paper presents an effective concept-based document classification system, which can efficiently classify Korean documents through the thesaurus tool. The thesaurus tool is the information extractor that acquires the meanings of document terms from the thesaurus. It supports effective document classification with the acquired meanings. The system uses the concept-probability vector to represent the meanings of the terms. Because the category of the document depends on the meanings than the terms, even though the size of the vector is small, the system can classify the document without degradation of the performance. The system uses the small concept-probability vector so that it can save the time and space for document classification. The experimental results suggest that the presented system with the thesaurus tool can effectively classify the documents.

A Collecting Model of Public Opinion on Social Disaster in Twitter: A Case Study in 'Humidifier Disinfectant'

The abstract should concisely state what was done, how it was done, principal results, and their significance. It should be less than 300 words for all forms of publication. Recently social disasters have been occurring frequently in the increasing complicated social structure, and the scale of damage has also become larger. Accordingly, there is a need for a way to prevent further damage by rapidly responding to social disasters. Twitter is attracting attention as a countermeasure against disasters because of immediacy and expandability. Especially, collecting public opinion on Twitter can be used as a useful tool to prevent disasters by quickly responding. This study proposes a collecting method of Twitter public opinion through keyword analysis, issue topic tweet detection, and time trend analysis. Furthermore we also show the feasibility by selecting the case of humidifier disinfectant which is a social issue recently.

Merging and Re-ranking Answers from Distributed Multiple Web Sources

Depending on questions, various answering methods and answer sources can be used. In this paper, we build a distributed QA system to handle different types of questions and web sources. When a user question is entered, the broker distributes the question over multiple sub-QAs according to question types. The selected sub-QAs find local optimal candidate answers, and then they are collected in to the answer manager. The merged candidates are re-ranked by adjusting confidence weights based on the question analysis result. The re-ranking algorithm aims to find global optimal answers. We borrow the concept from the margin and slack variables in SVM, and modify to project confidence weights into the same boundary by training. Several experimental results prove reliability of our proposed QA model.