@inproceedings{chrupala2010named, author = {Chrupala, Grzegorz and Klakow, Dietrich}, booktitle = {LREC}, crossref = {conf/lrec/2010}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, ee = {http://www.lrec-conf.org/proceedings/lrec2010/summaries/538.html}, interhash = {85b8f5e04b66df3fe9411fc8f81ae43a}, intrahash = {68b98f37dc2dd0a89f580d9e6b65c780}, isbn = {2-9517408-6-7}, publisher = {European Language Resources Association}, title = {A Named Entity Labeler for German: Exploiting Wikipedia and Distributional Clusters.}, url = {http://lexitron.nectec.or.th/public/LREC-2010_Malta/pdf/538_Paper.pdf}, year = 2010 } @inproceedings{mihalcea2007wikify, abstract = {This paper introduces the use of Wikipedia as a resource for automatic keyword extraction and word sense disambiguation, and shows how this online encyclopedia can be used to achieve state-of-the-art results on both these tasks. The paper also shows how the two methods can be combined into a system able to automatically enrich a text with links to encyclopedic knowledge. Given an input document, the system identifies the important concepts in the text and automatically links these concepts to the corresponding Wikipedia pages. Evaluations of the system show that the automatic annotations are reliable and hardly distinguishable from manual annotations.}, acmid = {1321475}, address = {New York, NY, USA}, author = {Mihalcea, Rada and Csomai, Andras}, booktitle = {Proceedings of the sixteenth ACM Conference on information and knowledge management}, doi = {10.1145/1321440.1321475}, interhash = {8e00f4c1515b89a9a035c9d4b78d7bed}, intrahash = {4917a0c8eb1ea05b2d103166dfaeeb6e}, isbn = {978-1-59593-803-9}, location = {Lisbon, Portugal}, numpages = {10}, pages = {233--242}, publisher = {ACM}, title = {Wikify!: linking documents to encyclopedic knowledge}, url = {http://doi.acm.org/10.1145/1321440.1321475}, year = 2007 } @inproceedings{gunes2012eager, abstract = {Key to named entity recognition, the manual gazetteering of entity lists is a costly, errorprone process that often yields results that are incomplete and suffer from sampling bias. Exploiting current sources of structured information, we propose a novel method for extending minimal seed lists into complete gazetteers. Like previous approaches, we value W IKIPEDIA as a huge, well-curated, and relatively unbiased source of entities. However, in contrast to previous work, we exploit not only its content, but also its structure, as exposed in DBPEDIA. We extend gazetteers through Wikipedia categories, carefully limiting the impact of noisy categorizations. The resulting gazetteers easily outperform previous approaches on named entity recognition. }, author = {Gunes, Omer and Schallhart, Christian and Furche, Tim and Lehmann, Jens and Ngomo, Axel-Cyrille Ngonga}, booktitle = {Proceedings of the 3rd Workshop on the People's Web Meets NLP: Collaboratively Constructed Semantic Resources and their Applications to NLP}, interhash = {20c47a41c89ff6c2a8f7bb524185b8ac}, intrahash = {3eac4c009268cd4f2c264dd24053f8a6}, month = jul, organization = {Association for Computational Linguistics}, pages = {29--33}, title = {EAGER: extending automatically gazetteers for entity recognition}, url = {http://acl.eldoc.ub.rug.nl/mirror/W/W12/W12-4005.pdf}, year = 2012 } @article{ley2009lessons, abstract = {The DBLP Computer Science Bibliography evolved from an early small experimental Web server to a popular service for the computer science community. Many design decisions and details of the public XML-records behind DBLP never were documented. This paper is a review of the evolution of DBLP. The main perspective is data modeling. In DBLP persons play a central role, our discussion of person names may be applicable to many other data bases. All DBLP data are available for your own experiments. You may either download the complete set, or use a simple XML-based API described in an online appendix.}, acmid = {1687577}, author = {Ley, Michael}, interhash = {a75ae2987d55512b7d0731c7a11a1722}, intrahash = {bb968ff4ba9ae93bc80ba05d16a98ff4}, issn = {2150-8097}, issue_date = {August 2009}, journal = {Proceedings of the VLDB Endowment}, month = aug, number = 2, numpages = {8}, pages = {1493--1500}, publisher = {VLDB Endowment}, title = {DBLP: some lessons learned}, url = {http://dl.acm.org/citation.cfm?id=1687553.1687577}, volume = 2, year = 2009 } @phdthesis{leidner2007toponym, abstract = {Background. In the area of Geographic Information Systems (GIS), a shared discipline between informatics and geography, the term geo-parsing is used to describe the process of identifying names in text, which in computational linguistics is known as named entity recognition and classification (NERC). The term geo-coding is used for the task of mapping from implicitly geo-referenced datasets (such as structured address records) to explicitly geo-referenced representations (e.g., using latitude and longitude). However, present-day GIS systems provide no automatic geo-coding functionality for unstructured text. In Information Extraction (IE), processing of named entities in text has traditionally been seen as a two-step process comprising a flat text span recognition sub-task and an atomic classification sub-task; relating the text span to a model of the world has been ignored by evaluations such as MUC or ACE (Chinchor (1998); U.S. NIST (2003)). However, spatial and temporal expressions refer to events in space-time, and the grounding of events is a precondition for accurate reasoning. Thus, automatic grounding can improve many applications such as automatic map drawing (e.g. for choosing a focus) and question answering (e.g., for questions like How far is London from Edinburgh?, given a story in which both occur and can be resolved). Whereas temporal grounding has received considerable attention in the recent past (Mani and Wilson (2000); Setzer (2001)), robust spatial grounding has long been neglected. Concentrating on geographic names for populated places, I define the task of automatic Toponym Resolution (TR) as computing the mapping from occurrences of names for places as found in a text to a representation of the extensional semantics of the location referred to (its referent), such as a geographic latitude/longitude footprint. The task of mapping from names to locations is hard due to insufficient and noisy databases, and a large degree of ambiguity: common words need to be distinguished from proper names (geo/non-geo ambiguity), and the mapping between names and locations is ambiguous (London can refer to the capital of the UK or to London, Ontario, Canada, or to about forty other Londons on earth). In addition, names of places and the boundaries referred to change over time, and databases are incomplete. Objective. I investigate how referentially ambiguous spatial named entities can be grounded, or resolved, with respect to an extensional coordinate model robustly on open-domain news text. I begin by comparing the few algorithms proposed in the literature, and, comparing semiformal, reconstructed descriptions of them, I factor out a shared repertoire of linguistic heuristics (e.g. rules, patterns) and extra-linguistic knowledge sources (e.g. population sizes). I then investigate how to combine these sources of evidence to obtain a superior method. I also investigate the noise effect introduced by the named entity tagging step that toponym resolution relies on in a sequential system pipeline architecture. Scope. In this thesis, I investigate a present-day snapshot of terrestrial geography as represented in the gazetteer defined and, accordingly, a collection of present-day news text. I limit the investigation to populated places; geo-coding of artifact names (e.g. airports or bridges), compositional geographic descriptions (e.g. 40 miles SW of London, near Berlin), for instance, is not attempted. Historic change is a major factor affecting gazetteer construction and ultimately toponym resolution. However, this is beyond the scope of this thesis. Method. While a small number of previous attempts have been made to solve the toponym resolution problem, these were either not evaluated, or evaluation was done by manual inspection of system output instead of curating a reusable reference corpus. Since the relevant literature is scattered across several disciplines (GIS, digital libraries, information retrieval, natural language processing) and descriptions of algorithms are mostly given in informal prose, I attempt to systematically describe them and aim at a reconstruction in a uniform, semi-formal pseudo-code notation for easier re-implementation. A systematic comparison leads to an inventory of heuristics and other sources of evidence. In order to carry out a comparative evaluation procedure, an evaluation resource is required. Unfortunately, to date no gold standard has been curated in the research community. To this end, a reference gazetteer and an associated novel reference corpus with human-labeled referent annotation are created. These are subsequently used to benchmark a selection of the reconstructed algorithms and a novel re-combination of the heuristics catalogued in the inventory. I then compare the performance of the same TR algorithms under three different conditions, namely applying it to the (i) output of human named entity annotation, (ii) automatic annotation using an existing Maximum Entropy sequence tagging model, and (iii) a na ̈ve toponym lookup procedure in a gazetteer. Evaluation. The algorithms implemented in this thesis are evaluated in an intrinsic or component evaluation. To this end, we define a task-specific matching criterion to be used with traditional Precision (P) and Recall (R) evaluation metrics. This matching criterion is lenient with respect to numerical gazetteer imprecision in situations where one toponym instance is marked up with different gazetteer entries in the gold standard and the test set, respectively, but where these refer to the same candidate referent, caused by multiple near-duplicate entries in the reference gazetteer. Main Contributions. The major contributions of this thesis are as follows: • A new reference corpus in which instances of location named entities have been manually annotated with spatial grounding information for populated places, and an associated reference gazetteer, from which the assigned candidate referents are chosen. This reference gazetteer provides numerical latitude/longitude coordinates (such as 51◦ 32 North, 0◦ 5 West) as well as hierarchical path descriptions (such as London > UK) with respect to a world wide-coverage, geographic taxonomy constructed by combining several large, but noisy gazetteers. This corpus contains news stories and comprises two sub-corpora, a subset of the REUTERS RCV1 news corpus used for the CoNLL shared task (Tjong Kim Sang and De Meulder (2003)), and a subset of the Fourth Message Understanding Contest (MUC-4; Chinchor (1995)), both available pre-annotated with gold-standard. This corpus will be made available as a reference evaluation resource; • a new method and implemented system to resolve toponyms that is capable of robustly processing unseen text (open-domain online newswire text) and grounding toponym instances in an extensional model using longitude and latitude coordinates and hierarchical path descriptions, using internal (textual) and external (gazetteer) evidence; • an empirical analysis of the relative utility of various heuristic biases and other sources of evidence with respect to the toponym resolution task when analysing free news genre text; • a comparison between a replicated method as described in the literature, which functions a baseline, and a novel algorithm based on minimality heuristics; and • several exemplary prototypical applications to show how the resulting toponym resolution methods can be used to create visual surrogates for news stories, a geographic exploration tool for news browsing, geographically-aware document retrieval and to answer spatial questions (How far...?) in an open-domain question answering system. These applications only have demonstrative character, as a thorough quantitative, task-based (extrinsic) evaluation of the utility of automatic toponym resolution is beyond the scope of this thesis and left for future work. }, author = {Leidner, Jochen Lothar}, interhash = {4558afaf4c48986f34b04bf06169456e}, intrahash = {c5f99e5f0fc60d29fcf730b968a95e90}, school = {School of Informatics, University of Edinburgh}, title = {Toponym Resolution in Text: Annotation, Evaluation and Applications of Spatial Grounding of Place Names}, url = {http://www.era.lib.ed.ac.uk/bitstream/1842/1849/1/leidner-2007-phd.pdf}, year = 2007 } @inproceedings{garbin2005disambiguating, abstract = {This research is aimed at the problem of disambiguating toponyms (place names) in terms of a classification derived by merging information from two publicly available gazetteers. To establish the difficulty of the problem, we measured the degree of ambiguity, with respect to a gazetteer, for toponyms in news. We found that 67.82% of the toponyms found in a corpus that were ambiguous in a gazetteer lacked a local discriminator in the text. Given the scarcity of human-annotated data, our method used unsupervised machine learning to develop disambiguation rules. Toponyms were automatically tagged with information about them found in a gazetteer. A toponym that was ambiguous in the gazetteer was automatically disambiguated based on preference heuristics. This automatically tagged data was used to train a machine learner, which disambiguated toponyms in a human-annotated news corpus at 78.5% accuracy.}, acmid = {1220621}, address = {Stroudsburg, PA, USA}, author = {Garbin, Eric and Mani, Inderjeet}, booktitle = {Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing}, doi = {10.3115/1220575.1220621}, interhash = {566910cb6e9745ee70da19d2ccafaffa}, intrahash = {de574cf3bff3a3748fcd9bd5a9a0f3d1}, location = {Vancouver, British Columbia, Canada}, numpages = {8}, pages = {363--370}, publisher = {Association for Computational Linguistics}, title = {Disambiguating toponyms in news}, url = {http://dx.doi.org/10.3115/1220575.1220621}, year = 2005 } @article{song2012video, abstract = {This paper considers the problem of web video geolocation: we hope to determine where on the Earth a web video was taken. By analyzing a 6.5-million geotagged web video dataset, we observe that there exist inherent geography intimacies between a video with its relevant videos (related videos and same-author videos). This social relationship supplies a direct and effective cue to locate the video to a particular region on the earth. Based on this observation, we propose an effective web video geolocation algorithm by propagating geotags among the web video social relationship graph. For the video that have no geotagged relevant videos, we aim to collect those geotagged relevant images that are content similar with the video (share some visual or textual information with the video) as the cue to infer the location of the video. The experiments have demonstrated the effectiveness of both methods, with the geolocation accuracy much better than state-of-the-art approaches. Finally, an online web video geolocation system: Video2Locatoin (V2L) is developed to provide public access to our algorithm.}, author = {Song, Yi-Cheng and Zhang, Yong-Dong and Cao, Juan and Xia, Tian and Liu, Wu and Li, Jin-Tao}, doi = {10.1109/TMM.2011.2172937}, interhash = {090791b9f4e0737f35e40af91c4475d2}, intrahash = {40d777e2e4a83e28c75a1c8ba0554153}, issn = {1520-9210}, journal = {Transactions on Multimedia}, month = apr, number = 2, pages = {456--470}, publisher = {IEEE}, title = {Web Video Geolocation by Geotagged Social Resources}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6054059}, volume = 14, year = 2012 } @inproceedings{fink2009geolocation, abstract = {Understanding the spatial distribution of people who author social media content is of growing interest for researchers and commerce. Blogging platforms depend on authors reporting their own location. However, not all authors report or reveal their location on their blog's home page. Automated geolocation strategies using IP address and domain name are not adequate for determining an author's location because most blogs are not self-hosted. In this paper we describe a method that uses the place name mentions in a blog to determine an author's location. We achieved an accuracy of 63% on a collection of 844 blogs with known locations.}, author = {Fink, C. and Piatko, C. and Mayfield, J. and Chou, D. and Finin, T. and Martineau, J.}, booktitle = {Proceedings of the International Conference on Computational Science and Engineering}, doi = {10.1109/CSE.2009.584}, interhash = {59b768c08026047c20d472ff93a4d513}, intrahash = {70eddd59803db7efee4b8c840fe5a79b}, month = aug, pages = {1088--1092}, title = {The Geolocation of Web Logs from Textual Clues}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5282996}, volume = 4, year = 2009 } @inproceedings{martins2008extracting, abstract = {Geo-temporal criteria are important for filtering, grouping and prioritizing information resources. This presents techniques for extracting semantic geo-temporal information from text, using simple text mining methods that leverage on a gazetteer. A prototype system, implementing the proposed methods and capable of displaying information over maps and timelines, is described. This prototype can take input in RSS, demonstrating the application to content from many different online sources. Experimental results demonstrate the efficiency and accuracy of the proposed approaches.}, author = {Martins, B. and Manguinhas, H. and Borbinha, J.}, booktitle = {Proceedings of the International Conference on Semantic Computing}, doi = {10.1109/ICSC.2008.86}, interhash = {d03fecb6b3261ffa0a5e11789b188883}, intrahash = {5a889bc7d9e81cb1d294cb83b767bf64}, month = aug, pages = {1--9}, publisher = {IEEE Computer Society}, title = {Extracting and Exploring the Geo-Temporal Semantics of Textual Resources}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4597167}, year = 2008 } @inproceedings{tezuka2001webbased, abstract = {Dealing with prepositions such as "near", "between" and "in front of" is very important in geographic information systems (GISs). In most systems, real-world distances are used to handle these prepositions. One of the difficulties in processing these prepositions lies in the fact that their geographical range is distorted in people's cognitive maps. For example, the size of an area referred to by the preposition "near" gets narrowed when a more famous landmark exists right next to the base geographical object. This is because users are likely to choose the most famous landmark when referring to a certain position. Also, the area referred to by "between" is not a straight line; it curves along the most commonly used pathway between the base objects. The difference in the popularity of geographical objects is the main reason for causing such distortions in cognitive maps. Since there is a large amount of data on the World Wide Web, we believe that such conceptual distortion can be calculated by analyzing Web data. Popularity and co-occurrence rates are calculated through their frequency in Web resources. Inference rules are set to restrict the target of conceptual prepositions using GISs and information obtained from the Web}, author = {Tezuka, T. and Lee, Ryong and Kambayashi, Y. and Takakura, H.}, booktitle = {Proceedings of the Second International Conference on Web Information Systems Engineering}, doi = {10.1109/WISE.2001.996692}, interhash = {132a7e8b5e47313ce56c790188d4d384}, intrahash = {b5b4d65538c9253a2b43c6252521d4f4}, month = dec, pages = {14--21}, title = {Web-based inference rules for processing conceptual geographical relationships}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=996692&tag=1}, volume = 2, year = 2001 } @inproceedings{clough2004proposal, author = {Clough, Paul and Sanderson, Mark}, booktitle = {Proceedings of the Workshop on Geographic Information Retrieval}, interhash = {d6d904074f6bd0fa1cee9c418a140ea4}, intrahash = {b7da956af5ed967d695770694f6ad783}, month = jul, title = {A proposal for comparative evaluation of automatic annotation for geo-referenced documents}, url = {http://eprints.whiterose.ac.uk/4522/}, year = 2004 } @article{tejada2001learning, abstract = {When integrating information from multiple websites, the same data objects can exist in inconsistent text formats across sites, making it difficult to identify matching objects using exact text match. We have developed an object identification system called Active Atlas, which compares the objects’ shared attributes in order to identify matching objects. Certain attributes are more important for deciding if a mapping should exist between two objects. Previous methods of object identification have required manual construction of object identification rules or mapping rules for determining the mappings between objects. This manual process is time consuming and error-prone. In our approach. Active Atlas learns to tailor mapping rules, through limited user input, to a specific application domain. The experimental results demonstrate that we achieve higher accuracy and require less user involvement than previous methods across various application domains.}, author = {Tejada, Sheila and Knoblock, Craig A and Minton, Steven}, doi = {10.1016/S0306-4379(01)00042-4}, interhash = {f9f59187b0397a0fbe1e558dfb4ad9cf}, intrahash = {5ad46801d602408ce271276f452263a9}, issn = {0306-4379}, journal = {Information Systems}, month = dec, number = 8, pages = {607--633}, title = {Learning object identification rules for information integration}, url = {http://www.sciencedirect.com/science/article/pii/S0306437901000424}, volume = 26, year = 2001 } @inproceedings{lafferty2001conditional, acmid = {655813}, address = {San Francisco, CA, USA}, author = {Lafferty, John D. and McCallum, Andrew and Pereira, Fernando C. N.}, booktitle = {Proceedings of the Eighteenth International Conference on Machine Learning}, interhash = {574c59001ecc3aa04850e1751d96c137}, intrahash = {180c5d6097317fa1b19ca8df75341230}, isbn = {1-55860-778-1}, numpages = {8}, pages = {282--289}, publisher = {Morgan Kaufmann Publishers Inc.}, title = {Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data}, url = {http://dl.acm.org/citation.cfm?id=645530.655813}, year = 2001 } @inproceedings{granitzer2012comparison, abstract = {Social research networks such as Mendeley and CiteULike offer various services for collaboratively managing bibliographic metadata. Compared with traditional libraries, metadata quality is of crucial importance in order to create a crowdsourced bibliographic catalog for search and browsing. Artifacts, in particular PDFs which are managed by the users of the social research networks, become one important metadata source and the starting point for creating a homogeneous, high quality, bibliographic catalog. Natural Language Processing and Information Extraction techniques have been employed to extract structured information from unstructured sources. However, given highly heterogeneous artifacts that cover a range of publication styles, stemming from different publication sources, and imperfect PDF processing tools, how accurate are metadata extraction methods in such real-world settings? This paper focuses on answering that question by investigating the use of Conditional Random Fields and Support Vector Machines on real-world data gathered from Mendeley and Linked-Data repositories. We compare style and content features on existing state-of-the-art methods on two newly created real-world data sets for metadata extraction. Our analysis shows that two-stage SVMs provide reasonable performance in solving the challenge of metadata extraction for crowdsourcing bibliographic metadata management.}, acmid = {2254154}, address = {New York, NY, USA}, articleno = {19}, author = {Granitzer, Michael and Hristakeva, Maya and Knight, Robert and Jack, Kris and Kern, Roman}, booktitle = {Proceedings of the 2nd International Conference on Web Intelligence, Mining and Semantics}, doi = {10.1145/2254129.2254154}, interhash = {bfa622b68be4bb039ca0516b3b33ec40}, intrahash = {7194c862da359af9aa18b4d865cbce55}, isbn = {978-1-4503-0915-8}, location = {Craiova, Romania}, numpages = {8}, pages = {19:1--19:8}, publisher = {ACM}, title = {A comparison of layout based bibliographic metadata extraction techniques}, url = {http://doi.acm.org/10.1145/2254129.2254154}, year = 2012 } @inproceedings{kristjansson2004interactive, abstract = {Information Extraction methods can be used to automatically "fill-in" database forms from unstructured data such as Web documents or email. State-of-the-art methods have achieved low error rates but invariably make a number of errors. The goal of an interactive information extraction system is to assist the user in filling in database fields while giving the user confidence in the integrity of the data. The user is presented with an interactive interface that allows both the rapid verification of automatic field assignments and the correction of errors. In cases where there are multiple errors, our system takes into account user corrections, and immediately propagates these constraints such that other fields are often corrected automatically. Linear-chain conditional random fields (CRFs) have been shown to perform well for information extraction and other language modelling tasks due to their ability to capture arbitrary, overlapping features of the input in aMarkov model. We apply this framework with two extensions: a constrained Viterbi decoding which finds the optimal field assignments consistent with the fields explicitly specified or corrected by the user; and a mechanism for estimating the confidence of each extracted field, so that low-confidence extractions can be highlighted. Both of these mechanisms are incorporated in a novel user interface for form filling that is intuitive and speeds the entry of data—providing a 23% reduction in error due to automated corrections.}, author = {Kristjansson, Trausti T. and Culotta, Aron and Viola, Paul A. and McCallum, Andrew}, booktitle = {AAAI}, editor = {McGuinness, Deborah L. and Ferguson, George}, interhash = {89fe7fe6ef4c088b10d3b0b0aabeaf46}, intrahash = {fe6cb1dbef3216852a63a625a30799d6}, isbn = {0-262-51183-5}, pages = {412--418}, publisher = {AAAI Press/The MIT Press}, title = {Interactive Information Extraction with Constrained Conditional Random Fields.}, url = {http://dblp.uni-trier.de/db/conf/aaai/aaai2004.html#KristjanssonCVM04}, year = 2004 } @article{raykar2010learning, abstract = {For many supervised learning tasks it may be infeasible (or very expensive) to obtain objective and reliable labels. Instead, we can collect subjective (possibly noisy) labels from multiple experts or annotators. In practice, there is a substantial amount of disagreement among the annotators, and hence it is of great practical interest to address conventional supervised learning problems in this scenario. In this paper we describe a probabilistic approach for supervised learning when we have multiple annotators providing (possibly noisy) labels but no absolute gold standard. The proposed algorithm evaluates the different experts and also gives an estimate of the actual hidden labels. Experimental results indicate that the proposed method is superior to the commonly used majority voting baseline.}, acmid = {1859894}, author = {Raykar, Vikas C. and Yu, Shipeng and Zhao, Linda H. and Valadez, Gerardo Hermosillo and Florin, Charles and Bogoni, Luca and Moy, Linda}, interhash = {8113daf47997fddf48e4c6c79f2eba56}, intrahash = {14220abe8babfab01c0cdd5ebd5e4b7c}, issn = {1532-4435}, issue_date = {3/1/2010}, journal = {Journal of Machine Learning Research}, month = aug, numpages = {26}, pages = {1297--1322}, publisher = {JMLR.org}, title = {Learning From Crowds}, url = {http://dl.acm.org/citation.cfm?id=1756006.1859894}, volume = 11, year = 2010 } @article{balke2012introduction, abstract = {Transforming unstructured or semi-structured information into structured knowledge is one of the big challenges of today’s knowledge society. While this abstract goal is still unreached and probably unreachable, intelligent information extraction techniques are considered key ingredients on the way to generating and representing knowledge for a wide variety of applications. This is especially true for the current efforts to turn the World Wide Web being the world’s largest collection of information into the world’s largest knowledge base. This introduction gives a broad overview about the major topics and current trends in information extraction.}, address = {Berlin/Heidelberg}, affiliation = {Institut für Informationssysteme, Technische Universität Braunschweig, Braunschweig, Germany}, author = {Balke, Wolf-Tilo}, doi = {10.1007/s13222-012-0090-x}, interhash = {0127ba6c59c3f7f7121429eb098a4b90}, intrahash = {992b3c989c8fda7c58cd9262e2f70907}, issn = {1618-2162}, journal = {Datenbank-Spektrum}, keyword = {Computer Science}, number = 2, pages = {81--88}, publisher = {Springer}, title = {Introduction to Information Extraction: Basic Notions and Current Trends}, url = {http://dx.doi.org/10.1007/s13222-012-0090-x}, volume = 12, year = 2012 } @incollection{li2011incorporating, abstract = {In scientific cooperation network, ambiguous author names may occur due to the existence of multiple authors with the same name. Users of these networks usually want to know the exact author of a paper, whereas we do not have any unique identifier to distinguish them. In this paper, we focus ourselves on such problem, we propose a new method that incorporates user feedback into the model for name disambiguation of scientific cooperation network. Perceptron is used as the classifier. Two features and a constraint drawn from user feedback are incorporated into the perceptron to enhance the performance of name disambiguation. Specifically, we construct user feedback as a training stream, and refine the perceptron continuously. Experimental results show that the proposed algorithm can learn continuously and significantly outperforms the previous methods without introducing user interactions.}, address = {Berlin/Heidelberg}, affiliation = {Intelligent and Distributed Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074 P.R. China}, author = {Li, Yuhua and Wen, Aiming and Lin, Quan and Li, Ruixuan and Lu, Zhengding}, booktitle = {Web-Age Information Management}, doi = {10.1007/978-3-642-23535-1_39}, editor = {Wang, Haixun and Li, Shijun and Oyama, Satoshi and Hu, Xiaohua and Qian, Tieyun}, interhash = {3baace12cb4481dcceb53c2d47f413b5}, intrahash = {96f2ae8551126527c2dfe69c8fa22f6c}, isbn = {978-3-642-23534-4}, keyword = {Computer Science}, pages = {454--466}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Incorporating User Feedback into Name Disambiguation of Scientific Cooperation Network}, url = {http://dx.doi.org/10.1007/978-3-642-23535-1_39}, volume = 6897, year = 2011 } @article{lofi2012information, abstract = {Recent years brought tremendous advancements in the area of automated information extraction. But still, problem scenarios remain where even state-of-the-art algorithms do not provide a satisfying solution. In these cases, another aspiring recent trend can be exploited to achieve the required extraction quality: explicit crowdsourcing of human intelligence tasks. In this paper, we discuss the synergies between information extraction and crowdsourcing. In particular, we methodically identify and classify the challenges and fallacies that arise when combining both approaches. Furthermore, we argue that for harnessing the full potential of either approach, true hybrid techniques must be considered. To demonstrate this point, we showcase such a hybrid technique, which tightly interweaves information extraction with crowdsourcing and machine learning to vastly surpass the abilities of either technique.}, address = {Berlin/Heidelberg}, affiliation = {Institut für Informationssysteme, Technische Universität Braunschweig, Braunschweig, Germany}, author = {Lofi, Christoph and Selke, Joachim and Balke, Wolf-Tilo}, doi = {10.1007/s13222-012-0092-8}, interhash = {941feeaa7bb134e0a5f8b5c0225756b8}, intrahash = {37cc8f1d19105a073544d6594fbbc033}, issn = {1618-2162}, journal = {Datenbank-Spektrum}, keyword = {Computer Science}, number = 2, pages = {109--120}, publisher = {Springer}, title = {Information Extraction Meets Crowdsourcing: A Promising Couple}, url = {http://dx.doi.org/10.1007/s13222-012-0092-8}, volume = 12, year = 2012 } @inproceedings{paton2011feedback, abstract = {User feedback is gaining momentum as a means of addressing the difficulties underlying information integration tasks. It can be used to assist users in building information integration systems and to improve the quality of existing systems, e.g., in dataspaces. Existing proposals in the area are confined to specific integration sub-problems considering a specific kind of feedback sought, in most cases, from a single user. We argue in this paper that, in order to maximize the benefits that can be drawn from user feedback, it should be considered and managed as a first class citizen. Accordingly, we present generic operations that underpin the management of feedback within information integration systems, and that are applicable to feedback of different kinds, potentially supplied by multiple users with different expectations. We present preliminary solutions that can be adopted for realizing such operations, and sketch a research agenda for the information integration community.}, author = {Paton, Norman W. and Fernandes, Alvaro A. A. and Hedeler, Cornelia and Embury, Suzanne M.}, booktitle = {Proceedings of the Conference on Innovative Data Systems Research (CIDR)}, interhash = {1874e5c09919244808457021d2d884d1}, intrahash = {cd75210156615616e4f25c91143040c4}, pages = {175--183}, title = {User Feedback as a First Class Citizen in Information Integration Systems}, url = {http://www.cidrdb.org/cidr2011/Papers/CIDR11_Paper21.pdf}, year = 2011 }