Towards Web-Scale Collaborative Knowledge Extraction

Today, we can nd a vast amount of textual information stored in proprietary data stores. The experience of search- ing information in these systems could be improved in a remarkable manner if we combine these private data stores with the information supplied by the Internet, merging both data sources to get new knowledge. In this paper, we pro- pose an architecture with the goal of automatically obtain- ing knowledge about entities (e.g., persons, places, organi- zations, etc.) from a set of natural text documents, building smart data from raw data. We have tested the system in the context of the news archive of a real Media Group.

2015

The Digital Libraries community has shown over the last years a growing interest in Semantic Search technologies. Content analysis and annotation is a vital task, but for large corpora it’s not feasible to do it manually. Several automatic tools are available, but such tools usually provide little tuning possibilities and do not support integration with different systems. Search and adaptation technologies, on the other hand, are becoming increasingly multi-lingual and cross-domain to tackle the continuous growth of the available information. So, we claim that to tackle such criticalities a more systematic and flexible approach, such as the use of a framework, is needed. In this paper we present a novel framework for Knowledge Extraction, whose main goal is to support the development of new applications and to ease the integration of

2010

1 Overview and Motivation (to be used as abstract) The Web bears the potential of being the world’s greatest enc yclopedic source, but we are far from fully exploiting this potential. Valuable scientific and cultural c ontent is interspersed with a huge amount of noisy, lowquality, unstructured text and media. The proliferation of knowledge-sharing communities like Wikipedia and the advances in automated information extraction from Web pages give rise to an unprecedented opportunity: Can we systematically harvest facts from the Web and compile them into a comprehensive machine-readable knowledge base?Such a knowledge base would contain not only the world’s enti ties, but also their semantic properties, and their relationships with each other. Imagi ne a “Structured Wikipedia” that has the same scale and richness as Wikipedia itself, but offers a precise and co ncise representation of knowledge, e.g., in the RDF format. This would enable expressive and highly precise querying, e.g., ...

International Journal of Mechanical Engineering and Information Technology, 2015

Extracting useful information from World Wide Web is an important and challenging problem. Information Extraction (IE) task is an interesting area that is used in getting a useful information. The traditional information extraction systems are focused on satisfying precise, narrow and pre-specified requests from small homogenous corpora. Applying these systems on another domain or a large scale heterogeneous corpus is a complex task. Information Extraction has traditionally relied on extensive human involvement in the form of hand-crafted extraction rules or hand-tagged training examples. The main contribution is how to help the user to extract relevant information from different and changeable web pages and integrate this extracted information into a single structured file automatically. Social networks play an important role in the semantic web. According to the intention of utilizing the social networks for the semantic web, several studies have been examined the automatic information extraction from social networks. This survey explores the different information extraction methods, tasks, applications, system development and how to evaluate their performance. In addition to introduce a view on the most used approaches in extracting information from social networks.

Cases on Open-Linked Data and Semantic Web Applications

In this chapter we present the analysis of the Wikipedia collection by means of the ELiDa framework with the aim of enriching linked data. ELiDa is based on association rule mining, an exploratory technique to discover relevant correlations hidden in the analyzed data. To compactly store the large volume of extracted knowledge and efficiently retrieve it for further analysis, a persistent structure has been exploited. The domain expert is in charge of selecting the relevant knowledge by setting filtering parameters, assessing the quality of the extracted knowledge, and enriching the knowledge with the semantic expressiveness which cannot be automatically inferred. We consider, as representative document collections, seven datasets extracted from the Wikipedia collection. Each dataset has been analyzed from two point of views (i.e., transactions by documents, transactions by sentences) to highlight relevant knowledge at different levels of abstraction.

This work analyzes research gaps and challenges for Web-scale Information Extraction and foresees the usage of Linked Open Data as a groundbreaking solution for the field. The paper presents a novel methodology for Web scale Information Extraction which will be the core of the LODIE project (Linked Open Data Information Extraction). LODIE aims to develop Information Extraction techniques able to (i) scale at web level and (ii) adapt to user information need. We argument that for the first time in the history of IE this will be possible given the availability of Linked Data, a very large-scale information resource, providing annotated data on a growing number of domains.

ACM SIGWEB Newsletter, 2014

Information Extraction (IE) is the technique for transforming textual data into structured representation that can be understood by machines. It is a crucial technique in enabling the Semantic Web, where increasing interest has been seen in recent years. This article reports recent progress in the LODIE project - Linked Open Data for Information Extraction, aimed at advancing Web IE to a new frontier by exploiting largely available, semantically annotated, Linked Open Data as background knowledge. We cover topics of wrapper induction, IE from semi-structured content such as tables and lists, and IE from free-text. We describe new challenges in the research and methods proposed to address them, together with summaries of recent evaluations showing encouraging results.

International Symposium on Wearable Computers, 2003

The approach towards Semantic Web Information Extraction (IE) presented here is implemented in KIM - a platform for semantic indexing, annotation, and retrieval. It combines IE based on the mature text engineering platform (GATE1) with Semantic Web-compliant knowledge representation and management. The cornerstone is automatic generation of named-entity (NE) annotations with class and instance references to a semantic repository. Simplistic

IEICE Transactions on Information and Systems

As the manual creation of domain models and also of linked data is very costly, the extraction of knowledge from structured and unstructured data has been one of the central research areas in the Semantic Web field in the last two decades. Here, we look specifically at the extraction of formalized knowledge from natural language text, which is the most abundant source of human knowledge available. There are many tools on hand for information and knowledge extraction for English natural language, for written Thai language the situation is different. The goal of this work is to assess the state-of-the-art of research on formal knowledge extraction specifically from Thai language text, and then give suggestions and practical research ideas on how to improve the state-of-the-art. To address the goal, first we distinguish nine knowledge extraction for the Semantic Web tasks defined in literature on knowledge extraction from English text, for example taxonomy extraction, relation extraction, or named entity recognition. For each of the nine tasks, we analyze the publications and tools available for Thai text in the form of a comprehensive literature survey. Additionally to our assessment, we measure the self-assessment by the Thai research community with the help of a questionnaire-based survey on each of the tasks. Furthermore, the structure and size of the Thai community is analyzed using complex literature database queries. Combining all the collected information we finally identify research gaps in knowledge extraction from Thai language. An extensive list of practical research ideas is presented, focusing on concrete suggestions for every knowledge extraction task-which can be implemented and evaluated with reasonable effort. Besides the task-specific hints for improvements of the state-of-the-art, we also include general recommendations on how to raise the efficiency of the respective research community.