Automatic extraction of factual information from text and its integration in a knowledge base
Pages 718 - 737
Abstract
This paper focusses on the problem of text processing for the task of updating a knowledge base. The main issues addressed are the kind of knowledge needed for extracting facts conveyed in narrative texts as well as the design of a procedure to perform the parsing process independently of the domain. Our approach is based on categorizing texts from two points of view, one structural, related to the surface organization of the text, and the other conceptual, related to the content of the knowledge base. Temporal information is a relevant source of information in narratives and therefore we focus on this problem proposing a representation to handle temporal units explicitly at the semantic level as well as in the knowledge base. We have designed a system for understanding news and we describe COTEM, the implemented prototype operating in a financial domain.
References
[1]
{Allen-83} Allen, J.F. "Maintaining Knowledge about Temporal Intervals" Communications of the ACM, vol. 26, n. 11, pg. 832--843.
[2]
{BoBoBras-88} Borillo, A., Borillo, M., Bras, M. "A Temporal Reasoning Cognitive Approach", Workshop on Lexical Semantics and Artificial Intelligence, Toulouse, pg. 129--151.
[3]
{Castell-89} Castell, N. "Un model pel tractament de la informació temporal en un sistema de comprensió automàtica de noticies" (in Catalan) Ph. D. dissertation. Dept. LSI. Universitat Politènica de Catalunya. Published as Research Report LSI-89-32.
[4]
{CaDiMaVe-89} Castell, N., Díaz, L., Marti, M.A., Verdejo, M.F. "Estudi linguistic sobre l'expressió del temps a la narració periodistica: notícies sobre economia" (in catalan), Research Report LSI-89-31. Dept. LSI. Universitat Politècnica de Catalunya. Spain.
[5]
{CaMaVe-89} Castell, N., Marti. M.A., Verdejo, M.F. "Expression of time in news: Interpretation and Representation". To be published in Semantics of Time, Space, and Movement in Natural Language. Editors: M. Borillo, F.Nef. Editions Hermès.
[6]
{DeJong-79} DeJong, G.F. "Skimming Stories in Real Time: An Experiment in Integrated Understanding", R. Report #158. Dept. Computer Science. Yale University.
[7]
{Hornstein-77} Hornstein, N. "Towards a Theory of Tense", Linguistic Inquiry, vol.8, n.3. pg. 521--557.
[8]
{Isalshi-86} Isahara, H., Ishizaki, S. "Context Analysis for Japanese Text", COLING-86, pg. 244--246.
[9]
{Obermaier-85} Obermaier. K.K. "GROK - A knowledge-Based Text Processing System" Artificial Intelligence Applications Second Conference (IEEE), pg. 384--389.
[10]
{Reichenbach-47} Reichenbach, H. The Elements of Symbolic Logic. Macmillan, New York.
[11]
{SaFriLy-87} Sager, N., Friedman, C., Lyman, N. Medical Language Processing, Addison-Wesley
[12]
{Yip-85} Yip, K.M. "Tense, Aspect and the Cognitive Representation of Time" 10th. IJCAI, pg. 806--814.
[13]
{YouHa-85} Young, S.R., Hayes, P.J. "Automatic Classification and Summarization of Banking Telexes" Artificial Intelligence Applications Second Conference (IEEE), pg. 402--408.
Recommendations
Service Model of Knowledge Integration Base on Automatic Text Summarization
ICCSMT '23: Proceedings of the 2023 4th International Conference on Computer Science and Management TechnologyWith the advent of the era of big data, the number of various knowledge resources has exploded. A series of problems, such as information redundancy and knowledge overload, bring trouble to users ' reading and use. The generation of text knowledge ...
Knowledge structure, knowledge granulation and knowledge distance in a knowledge base
One of the strengths of rough set theory is the fact that an unknown target concept can be approximately characterized by existing knowledge structures in a knowledge base. Knowledge structures in knowledge bases have two categories: complete and ...
The Content Extraction Method of Webpage Information Based on Knowledge Base
CSO '12: Proceedings of the 2012 Fifth International Joint Conference on Computational Sciences and OptimizationWeb content extraction is actually the process of transforming web unstructured information into structured information. Knowledge base has the advantages of ordering information and knowledge, also be used conveniently. So it's convenient to retrieve ...
Comments
Information & Contributors
Information
Published In
Publisher
LE CENTRE DE HAUTES ETUDES INTERNATIONALES D'INFORMATIQUE DOCUMENTAIRE
Paris, France
Publication History
Published: 02 April 1991
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 26Total Downloads
- Downloads (Last 12 months)9
- Downloads (Last 6 weeks)1
Reflects downloads up to 06 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in