@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{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 } @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 } @article{doan2009information, abstract = {Over the past few years, we have been trying to build an end-to-end system at Wisconsin to manage unstructured data, using extraction, integration, and user interaction. This paper describes the key information extraction (IE) challenges that we have run into, and sketches our solutions. We discuss in particular developing a declarative IE language, optimizing for this language, generating IE provenance, incorporating user feedback into the IE process, developing a novel wiki-based user interface for feedback, best-effort IE, pushing IE into RDBMSs, and more. Our work suggests that IE in managing unstructured data can open up many interesting research challenges, and that these challenges can greatly benefit from the wealth of work on managing structured data that has been carried out by the database community.}, acmid = {1519106}, address = {New York, NY, USA}, author = {Doan, AnHai and Naughton, Jeffrey F. and Ramakrishnan, Raghu and Baid, Akanksha and Chai, Xiaoyong and Chen, Fei and Chen, Ting and Chu, Eric and DeRose, Pedro and Gao, Byron and Gokhale, Chaitanya and Huang, Jiansheng and Shen, Warren and Vuong, Ba-Quy}, doi = {10.1145/1519103.1519106}, interhash = {b80d6ce47b976503692def4e86b0097d}, intrahash = {fccc9f25a1c70cb71d3377a7ddfe1614}, issn = {0163-5808}, issue_date = {December 2008}, journal = {SIGMOD Record}, month = mar, number = 4, numpages = {7}, pages = {14--20}, publisher = {ACM}, title = {Information extraction challenges in managing unstructured data}, url = {http://doi.acm.org/10.1145/1519103.1519106}, volume = 37, year = 2009 } @inproceedings{chai2009efficiently, abstract = {Many applications increasingly employ information extraction and integration (IE/II) programs to infer structures from unstructured data. Automatic IE/II are inherently imprecise. Hence such programs often make many IE/II mistakes, and thus can significantly benefit from user feedback. Today, however, there is no good way to automatically provide and process such feedback. When finding an IE/II mistake, users often must alert the developer team (e.g., via email or Web form) about the mistake, and then wait for the team to manually examine the program internals to locate and fix the mistake, a slow, error-prone, and frustrating process.

In this paper we propose a solution for users to directly provide feedback and for IE/II programs to automatically process such feedback. In our solution a developer U uses hlog, a declarative IE/II language, to write an IE/II program P. Next, U writes declarative user feedback rules that specify which parts of P's data (e.g., input, intermediate, or output data) users can edit, and via which user interfaces. Next, the so-augmented program P is executed, then enters a loop of waiting for and incorporating user feedback. Given user feedback F on a data portion of P, we show how to automatically propagate F to the rest of P, and to seamlessly combine F with prior user feedback. We describe the syntax and semantics of hlog, a baseline execution strategy, and then various optimization techniques. Finally, we describe experiments with real-world data that demonstrate the promise of our solution.}, acmid = {1559857}, address = {New York, NY, USA}, author = {Chai, Xiaoyong and Vuong, Ba-Quy and Doan, AnHai and Naughton, Jeffrey F.}, booktitle = {Proceedings of the 35th SIGMOD international conference on Management of data}, doi = {10.1145/1559845.1559857}, interhash = {5860215447e374b059597c0e3864e388}, intrahash = {d6c9fbf442a935dc0618107f8fb54d44}, isbn = {978-1-60558-551-2}, location = {Providence, Rhode Island, USA}, numpages = {14}, pages = {87--100}, publisher = {ACM}, title = {Efficiently incorporating user feedback into information extraction and integration programs}, url = {http://doi.acm.org/10.1145/1559845.1559857}, year = 2009 } @inproceedings{827147, abstract = {In this paper, we propose a method for extracting bibliographic attributes from reference strings captured using Optical Character Recognition (OCR) and an extended hidden Markov model. Bibliographic attribute extraction can be used in two ways. One is reference parsing in which attribute values are extracted from OCR-processed references for bibliographic matching. The other is reference alignment in which attribute values are aligned to the bibliographic record to enrich the vocabulary of the bibliographic database. In this paper, we first propose a statistical model for attribute extraction that represents both the syntactical structure of references and OCR error patterns. Then, we perform experiments using bibliographic references obtained from scanned images of papers in journals and transactions and show that useful attribute values are extracted from OCR-processed references. We also show that the proposed model has advantages in reducing the cost of preparing training data, a critical problem in rule-based systems.}, address = {Washington, DC, USA}, author = {Takasu, Atsuhiro}, booktitle = {JCDL '03: Proceedings of the 3rd ACM/IEEE-CS joint conference on Digital libraries}, interhash = {324c5995d000ceffa826eb2950dcd52e}, intrahash = {73b4dff8c6fac17b3ea377ed5b162540}, isbn = {0-7695-1939-3}, pages = {49--60}, publisher = {IEEE Computer Society}, title = {Bibliographic attribute extraction from erroneous references based on a statistical model}, year = 2003 } @inproceedings{peng2004accurate, author = {Peng, Fuchun and McCallum, Andrew}, booktitle = {HLT-NAACL}, interhash = {8f9ef6b359fef3bd08bfed653fe1bb55}, intrahash = {8d04bc19e470fe4b98e15a27a1e6e7e9}, pages = {329--336}, title = {Accurate Information Extraction from Research Papers using Conditional Random Fields}, url = {http://acl.ldc.upenn.edu/hlt-naacl2004/main/pdf/176_Paper.pdf}, year = 2004 }