Semantic information extraction from images of complex documents

Even though the digital processing of documents is increasingly widespread in industry, printed documents are still largely in use. In order to process electronically the contents of printed documents, information must be extracted from digital images of documents. When dealing with complex documents, in which the contents of different regions and fields can be highly heterogeneous with respect to layout, printing quality and the utilization of fonts and typing standards, the reconstruction of the contents of documents from digital images can be a difficult problem. In the present article we present an efficient solution for this problem, in which the semantic contents of fields in a complex document are extracted from a digital image.

Information extraction from clinical and radiology notes for liver cancer staging

Thesis (Ph.D.)--University of Washington, 2016-06

Query rewriting in information retrieval: automatic context extraction from local user documents to improve query results

The central objective of research in Information Retrieval (IR) is to discover new techniques to retrieve relevant information in order to satisfy an Information Need. The Information Need is satisfied when relevant information can be provided to the user. In IR, relevance is a fundamental concept which has changed over time, from popular to personal, i.e., what was considered relevant before was information for the whole population, but what is considered relevant now is specific information for each user. Hence, there is a need to connect the behavior of the system to the condition of a particular person and his social context; thereby an interdisciplinary sector called Human-Centered Computing was born. For the modern search engine, the information extracted for the individual user is crucial. According to the Personalized Search (PS), two different techniques are necessary to personalize a search: contextualization (interconnected conditions that occur in an activity), and individualization (characteristics that distinguish an individual). This movement of focus to the individual's need undermines the rigid linearity of the classical model overtaken the ``berry picking'' model which explains that the terms change thanks to the informational feedback received from the search activity introducing the concept of evolution of search terms. The development of Information Foraging theory, which observed the correlations between animal foraging and human information foraging, also contributed to this transformation through attempts to optimize the cost-benefit ratio. This thesis arose from the need to satisfy human individuality when searching for information, and it develops a synergistic collaboration between the frontiers of technological innovation and the recent advances in IR. The search method developed exploits what is relevant for the user by changing radically the way in which an Information Need is expressed, because now it is expressed through the generation of the query and its own context. As a matter of fact the method was born under the pretense to improve the quality of search by rewriting the query based on the contexts automatically generated from a local knowledge base. Furthermore, the idea of optimizing each IR system has led to develop it as a middleware of interaction between the user and the IR system. Thereby the system has just two possible actions: rewriting the query, and reordering the result. Equivalent actions to the approach was described from the PS that generally exploits information derived from analysis of user behavior, while the proposed approach exploits knowledge provided by the user. The thesis went further to generate a novel method for an assessment procedure, according to the "Cranfield paradigm", in order to evaluate this type of IR systems. The results achieved are interesting considering both the effectiveness achieved and the innovative approach undertaken together with the several applications inspired using a local knowledge base.

Identification of "pathologs" (disease-related genes) from the RIKEN mouse cDNA dataset using human curation plus FACTS, a new biological information extraction system

Background: A major goal in the post-genomic era is to identify and characterise disease susceptibility genes and to apply this knowledge to disease prevention and treatment. Rodents and humans have remarkably similar genomes and share closely related biochemical, physiological and pathological pathways. In this work we utilised the latest information on the mouse transcriptome as revealed by the RIKEN FANTOM2 project to identify novel human disease-related candidate genes. We define a new term patholog to mean a homolog of a human disease-related gene encoding a product ( transcript, anti-sense or protein) potentially relevant to disease. Rather than just focus on Mendelian inheritance, we applied the analysis to all potential pathologs regardless of their inheritance pattern. Results: Bioinformatic analysis and human curation of 60,770 RIKEN full-length mouse cDNA clones produced 2,578 sequences that showed similarity ( 70 - 85% identity) to known human-disease genes. Using a newly developed biological information extraction and annotation tool ( FACTS) in parallel with human expert analysis of 17,051 MEDLINE scientific abstracts we identified 182 novel potential pathologs. Of these, 36 were identified by computational tools only, 49 by human expert analysis only and 97 by both methods. These pathologs were related to neoplastic ( 53%), hereditary ( 24%), immunological ( 5%), cardio-vascular (4%), or other (14%), disorders. Conclusions: Large scale genome projects continue to produce a vast amount of data with potential application to the study of human disease. For this potential to be realised we need intelligent strategies for data categorisation and the ability to link sequence data with relevant literature. This paper demonstrates the power of combining human expert annotation with FACTS, a newly developed bioinformatics tool, to identify novel pathologs from within large-scale mouse transcript datasets.

Semantic relations extraction from unstructured information for domain ontologies enrichment

Based in internet growth, through semantic web, together with communication speed improvement and fast development of storage device sizes, data and information volume rises considerably every day. Because of this, in the last few years there has been a growing interest in structures for formal representation with suitable characteristics, such as the possibility to organize data and information, as well as the reuse of its contents aimed for the generation of new knowledge. Controlled Vocabulary, specifically Ontologies, present themselves in the lead as one of such structures of representation with high potential. Not only allow for data representation, as well as the reuse of such data for knowledge extraction, coupled with its subsequent storage through not so complex formalisms. However, for the purpose of assuring that ontology knowledge is always up to date, they need maintenance. Ontology Learning is an area which studies the details of update and maintenance of ontologies. It is worth noting that relevant literature already presents first results on automatic maintenance of ontologies, but still in a very early stage. Human-based processes are still the current way to update and maintain an ontology, which turns this into a cumbersome task. The generation of new knowledge aimed for ontology growth can be done based in Data Mining techniques, which is an area that studies techniques for data processing, pattern discovery and knowledge extraction in IT systems. This work aims at proposing a novel semi-automatic method for knowledge extraction from unstructured data sources, using Data Mining techniques, namely through pattern discovery, focused in improving the precision of concept and its semantic relations present in an ontology. In order to verify the applicability of the proposed method, a proof of concept was developed, presenting its results, which were applied in building and construction sector.

A Concept of Semantics Extraction from Web Data by Induction of Fuzzy Ontologies

Traditionally, ontologies describe knowledge representation in a denotational, formalized, and deductive way. In addition, in this paper, we propose a semiotic, inductive, and approximate approach to ontology creation. We define a conceptual framework, a semantics extraction algorithm, and a first proof of concept applying the algorithm to a small set of Wikipedia documents. Intended as an extension to the prevailing top-down ontologies, we introduce an inductive fuzzy grassroots ontology, which organizes itself organically from existing natural language Web content. Using inductive and approximate reasoning to reflect the natural way in which knowledge is processed, the ontology’s bottom-up build process creates emergent semantics learned from the Web. By this means, the ontology acts as a hub for computing with words described in natural language. For Web users, the structural semantics are visualized as inductive fuzzy cognitive maps, allowing an initial form of intelligence amplification. Eventually, we present an implementation of our inductive fuzzy grassroots ontology Thus,this paper contributes an algorithm for the extraction of fuzzy grassroots ontologies from Web data by inductive fuzzy classification.

The last voyage of Capt. Sir John Ross ... to the Arctic regions for the discovery of a north west passage : performed in the years 1829-30-31-32 and 33 : to which is prefixed an abridgement of the former voyages of Captns. Ross, Parry & other celebrated navigators to the northern latitudes : compiled from authentic information and original documents transmitted by an officer attached to the last expedition ; illustrated by engravings from drawings taken on the spot /

"On the position of the north magnetic pole. (Supplement)": 44 p. at end.

American Unitarianism : or, a brief history of "The progress and present state of the Unitarian churches in America" : compiled from documents and information communicated by the Rev. James Freeman, D. D. and William Wells, Jun. Esq. of Boston, and from other Unitarian gentlemen in this country /

Extracted from the author's "Memoirs of the life of the Reverend Theophilus Lindsey" printed in London, 1812, and now published for the benefit of the Christian churches in this country without note or alteration.

Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction

Background and aims: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging.

Materials and methods: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: ‘semi-structured’ and ‘unstructured’. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry.

Results: The best result of 99.4% accuracy – which included only one semi-structured report predicted as unstructured – was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured.

Conclusions: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.

Knowledge extraction from medium voltage load diagrams to support the definition of electrical tariffs

With the electricity market liberalization, distribution and retail companies are looking for better market strategies based on adequate information upon the consumption patterns of its electricity customers. In this environment all consumers are free to choose their electricity supplier. A fair insight on the customer´s behaviour will permit the definition of specific contract aspects based on the different consumption patterns. In this paper Data Mining (DM) techniques are applied to electricity consumption data from a utility client’s database. To form the different customer´s classes, and find a set of representative consumption patterns, we have used the Two-Step algorithm which is a hierarchical clustering algorithm. Each consumer class will be represented by its load profile resulting from the clustering operation. Next, to characterize each consumer class a classification model will be constructed with the C5.0 classification algorithm.

Symbolic Knowledge Extraction from Trained Neural Networks Governed by Lukasiewicz Logics

This work describes a methodology to extract symbolic rules from trained neural networks. In our approach, patterns on the network are codified using formulas on a Lukasiewicz logic. For this we take advantage of the fact that every connective in this multi-valued logic can be evaluated by a neuron in an artificial network having, by activation function the identity truncated to zero and one. This fact simplifies symbolic rule extraction and allows the easy injection of formulas into a network architecture. We trained this type of neural network using a back-propagation algorithm based on Levenderg-Marquardt algorithm, where in each learning iteration, we restricted the knowledge dissemination in the network structure. This makes the descriptive power of produced neural networks similar to the descriptive power of Lukasiewicz logic language, minimizing the information loss on the translation between connectionist and symbolic structures. To avoid redundance on the generated network, the method simplifies them in a pruning phase, using the "Optimal Brain Surgeon" algorithm. We tested this method on the task of finding the formula used on the generation of a given truth table. For real data tests, we selected the Mushrooms data set, available on the UCI Machine Learning Repository.

Algorithms for information extraction and signal annotation on long-term biosignals using clustering techniques

Dissertação para obtenção do Grau de Mestre em Engenharia Biomédica

Monetary policy with signal extraction from the bond market

Monetary policy is conducted in an environment of uncertainty. This paper sets upa model where the central bank uses real-time data from the bond market togetherwith standard macroeconomic indicators to estimate the current state of theeconomy more efficiently, while taking into account that its own actions influencewhat it observes. The timeliness of bond market data allows for quicker responsesof monetary policy to disturbances compared to the case when the central bankhas to rely solely on collected aggregate data. The information content of theterm structure creates a link between the bond market and the macroeconomythat is novel to the literature. To quantify the importance of the bond market asa source of information, the model is estimated on data for the United Statesand Australia using Bayesian methods. The empirical exercise suggests that thereis some information in the US term structure that helps the Federal Reserve toidentify shocks to the economy on a timely basis. Australian bond prices seemto be less informative than their US counterparts, perhaps because Australia is arelatively small and open economy.

Brain dynamics sustaining rapid rule extraction from speech

Language acquisition is a complex process that requires the synergic involvement of different cognitive functions, which include extracting and storing the words of the language and their embedded rules for progressive acquisition of grammatical information. As has been shown in other fields that study learning processes, synchronization mechanisms between neuronal assemblies might have a key role during language learning. In particular, studying these dynamics may help uncover whether different oscillatory patterns sustain more item-based learning of words and rule-based learning from speech input. Therefore, we tracked the modulation of oscillatory neural activity during the initial exposure to an artificial language, which contained embedded rules. We analyzed both spectral power variations, as a measure of local neuronal ensemble synchronization, as well as phase coherence patterns, as an index of the long-range coordination of these local groups of neurons. Synchronized activity in the gamma band (2040 Hz), previously reported to be related to the engagement of selective attention, showed a clear dissociation of local power and phase coherence between distant regions. In this frequency range, local synchrony characterized the subjects who were focused on word identification and was accompanied by increased coherence in the theta band (48 Hz). Only those subjects who were able to learn the embedded rules showed increased gamma band phase coherence between frontal, temporal, and parietal regions.