University, Diss., 2000--Bonn.

Relationship extraction is the task of extracting semantic relationships between en- tities from a text. We create a Czech Relationship Extraction Dataset (CERED) using distant supervision on Wikidata and Czech Wikipedia. We detail the methodology we used and the pitfalls we encountered. Then we use CERED to fine-tune a neural network model for relationship extraction. We base our model on BERT - a linguistic model pre-trained on extensive unlabeled data. We demonstrate that our model performs well on existing English relationship datasets (Semeval 2010 Task 8, TACRED) and report the results we achieved on CERED. 1

Entity Relationship (ER) diagrams are among the most popular formalisms for the support of database design [7, 12, 17, 6]. Their classical use in the (usually computer aided) database design process can roughly be described as follows: after evaluating the requirements of the application, the database designer constructs an ER schema, which represents the conceptual model of the new database. CASE tools can be used to automatically transform the ER schema into a relational database schema, which is then manually fine-tuned. During the last years, the initially rather simple ER formalisms has been extended by various means of expressivity to account for new, more complex application areas such as schema integration for data warehouses [12, 3, 13]. Designing a conceptual model with such enriched ER diagrams is a nontrivial task: there exist complex interactions between the various means of expressivity, which quite often result in unnoticed inconsistencies in the ER schemas and in implicit ramifications of the modeling that have not been intended by the designer. To address this problem, Description Logics (DLs) have been proposed and succesfully used as a tool for reasoning about ER diagrams and thereby detecting the aforementioned anomalies [5, 6, 8].

Ocean ambient noise is one of the important parameters which affect sonar system performance. If the ocean ambient noise is estimated accurately, the prediction accuracy of sonar system performance can be promoted significantly. Ocean ambient noise includes various and diverse sources, so the characteristics of the ocean ambient noise should be analyzed by long-term observations and statistical methods. Therefore, ocean ambient noise database was developed to facilitate management, preservation, and application of these datasets which increase with time. There were two datasets of acoustic and three datasets of wind speed in this database at this point. To develop this database systematically, this study applied Entity-Relationship Model to describe the relationship between different data and Relational Model to design the required categories. The database was constructed based on Microsoft Office Access, and user-friendly graphical interfaces based on MATLAB were provided for users: wind speed regression, time series, spectrogram, and spectrum tendency for users to query the database. As the results of analysis, the intermittent, unknown, and high-level sources at southwestern sea of Taiwan in spring and summer made the noise level of low frequency about 8 to 10 dB higher in the night-time than that in the day-time. According to wind speed regression analysis, if there were sufficient data, the method would be practicable to pick a wind speed data nearby the location of acoustic data for noise estimation. As the results of the typhoon effects analysis, the noise level of 1 to 8 kHz was increased significantly by typhoons. Besides, the noise level didn¡¦t decrease immediately and significantly after the pass of typhoon because of southwestern air current caused typhoon. After the database was developed, new acoustic data will keep being measured and collected, and the network capability will be integrated into the database to make the database more accessible to users.

Zugl.: Münster (Westfalen), Univ., Diss., 2005

University, Diss., 2005--Münster (Westfalen).

1 Modellierung im allgemeinen und in der Informatik - 2 Das Entity-Relationship-Modell - 3 Das Relationenmodell

No description available.

MEDLINE, a large and constantly increasing collection of biomedical article references, has been the source of numerous investigations related to textual information retrieval and knowledge capture, including article categorization, bibliometric analysis, semantic query answering, and biological concept recognition and relationship extraction. This dissertation discusses the design and development of novel methods that contribute to the tasks of document categorization and relationship extraction. The two investigations result in a fast tool for building descriptive models capable of categorizing documents to multiple labels and a highly effective method able to extract broad range of relationships between entities embedded in text. Additionally, an application that aims at representing the extracted knowledge in a strictly defined but highly expressive structure of ontology is presented. The classification of documents is based on an idea of building association rules that consist of frequent patterns of words appearing in documents and classes these patterns are likely to be assigned to. The process of building the models is based on a tree enumeration technique and dataset projection. The resulting algorithm offers two different tree traversing strategies, breadth-first and depth-first. The classification scenario involves the use of two alternative thresholding strategies based on either the document-independent confidence of the rules or a similarity measure between a rule and a document. The presented classification tool is shown to perform faster than other methods and is the first associative-classification solution to incorporate multiple classes and the information about recurrence of words in documents. The extraction of relations between entities embedded in text involves the utilization of the output of a constituent parser and a set of manually developed tree-like patterns. Both serve as the input of a novel algorithm that solves the newly formulated problem of constrained constituent tree inclusion with regular expression matching. The proposed relation extraction method is demonstrated to be parser-independent and outperforms in terms of effectiveness dependency-parser-based and machine-learning-based solutions. The extracted knowledge is further embedded in an existing ontology, which together with the structure-driven modification of the ontology results in a comprehensible, inference-consistent knowledge base constituting a tangible representation of knowledge and a potential component of applications such as semantically enhanced query answering systems.

The goal of development of sound database for marine fishes in Taiwan not only preserves data, but also wants to provide a common ground of data sharing to increase the efficiency for the study of fish behavior, automatic recognition, localization, and tracking. In order to provide the sound quality in terms of signal-to-noise ratio to users, the fish sound recording will be analyzed before uploading. Because most available data were recorded either in the field or in fish tank, the fish sounds were extracted by using two different automatic detection methods. If fish sound recordings were from the field, the Time Endpoint Detection was applied by the processing a 0.5-s time frame with 50 % overlapping. Then the energy of the time frame was obtained by the sum of square of amplitude and the median of the energy plus a standard deviation was established as the threshold to extract fish sounds. If the recording was made in the fish tank, the Frequency Endpoint Detection was applied by 0.5-s time frame with 50 % overlapping. Then each time frame will be transformed into spectrum and the energy ratio of each frequency will be calculated from the spectrum. Finally the information entropy was obtained from the energy ratio and the detection threshold was set on standard deviation above the median of the information entropy. From two different automatic detection methods, the sound quality was presented in the signal-to-noise ratio, which was the average power of signal divided by average power of the background noise. The fish sound database was a 3-Tier system and developed by PHP and MySQL. In order to reduce the storage size and maintain the integrity of data, the Relational Model was applied. Firstly, the recording data were conceptually represented as Entity-Relationship Diagram(ERD). Secondly, the ERD was transformed to relational schemas. Thirdly, the schemas was normalized by first, second, and third forms. To improve the users¡¦ efficiency the sound database provides three interfaces. One was data uploading, another was data searching according to the keyword of creature name, recording area, and recording time, the other was data comparing by recording number.