http://www.bibsonomy.org/burst/user/diego_ma/named_entitiesBibSonomy RSS feed for /user/diego_ma/named_entities2010-03-21T18:46:03+01:00http://www.bibsonomy.org/bibtex/26331703e11ece23065a9fda52e0827ad/diego_madiego_ma2009-07-06T10:21:03+02:00named_entities survey <span style="color:#555555;">Nadeau, <a href="http://www.bibsonomy.org/author/David">David</a> and Sekine, <a href="http://www.bibsonomy.org/author/Satoshi">Satoshi</a> </span><em>Journal of Linguisticae Investigationes</em><em>30(1):1-20</em>(<em>2007</em>)Mon Jul 06 10:21:03 CEST 2009Journal of Linguisticae Investigationes11-20A Survey of Named Entity Recognition and Classification302007named_entities survey http://www.bibsonomy.org/bibtex/264e2ff61c23df0f5f02914ea091dc158/diego_madiego_ma2008-10-10T05:18:00+02:00named_entities AnswerFinder molla_publication <span style="color:#555555;">Diego <a href="http://www.bibsonomy.org/author/Moll{\&#039;a}">Moll&#225;</a> and Menno van <a href="http://www.bibsonomy.org/author/Zaanen">Zaanen</a> and Daniel <a href="http://www.bibsonomy.org/author/Smith">Smith</a> </span><em>Proceedings ALTW 2006, </em><em>page 51-58. </em>(<em>2006</em>)Fri Oct 10 05:18:00 CEST 2008Proceedings ALTW 200651-58Named Entity Recognition for Question Answering2006named_entities AnswerFinder molla_publication Current text-based question answering (QA) systems usually contain a named entity recogniser (NER) as a core component. Named entity recognition as traditionally been developed as a component for information extraction systems, and current techniques are focused on this end use. However, no formal assessment has been done on the characteristics of a NER within the task of question answering. In this paper we present a NER that aims at higher recall by allowing multiple entity labels to strings. The NER is embedded in a question answering system and the overall QA system performance is compared to that of one with a traditional variation of the NER that only allows single entity labels. It is shown that the added noise produced introduced by the additional labels is offset by the higher recall gained, therefore enabling the QA system to have a better chance to find the answer.http://www.bibsonomy.org/bibtex/28d8585e90538626d8169eeeb8dda4d97/diego_madiego_ma2008-01-29T07:22:25+01:00AnswerFinder named_entities molla_publication <span style="color:#555555;">Menno van <a href="http://www.bibsonomy.org/author/Zaanen">Zaanen</a> and Diego <a href="http://www.bibsonomy.org/author/Moll\&#039;a">Moll\'a</a> </span><em>Proceedings PACLING 2007, </em>(<em>2007</em>)Tue Jan 29 07:22:25 CET 2008Proceedings PACLING 2007A Named Entity Recogniser for Question Answering2007AnswerFinder named_entities molla_publication Named Entity Recognisers (NERs) are typically used by question answering (QA) systems as means to preselect answer candidates. However, there has not been much work on the formal assessment of the use of NERs for QA nor on their optimal parameters. In this paper we investigate the main characteristics of a NER for QA. The results show that it is important to maintain high recall to retain all possible answers on the one hand, while high precision is essential during the final answer selection phase. We present a NER designed for QA, which aims at having a high recall.http://www.bibsonomy.org/bibtex/2202b97875a0ca06dba67da3f7febfc86/diego_madiego_ma2008-01-29T07:21:37+01:00AnswerFinder named_entities speech molla_publication <span style="color:#555555;">Diego <a href="http://www.bibsonomy.org/author/Moll{\&#039;a}">Moll&#225;</a> and Menno van <a href="http://www.bibsonomy.org/author/Zaanen">Zaanen</a> and Steve <a href="http://www.bibsonomy.org/author/Cassidy">Cassidy</a> </span><em>Proc. ALTW 2007, </em><em> 5, </em><em>page 57-65. </em>(<em>2007</em>)Tue Jan 29 07:21:37 CET 2008Proc. ALTW 200757-65Named Entity Recognition in Question Answering of Speech Data52007AnswerFinder named_entities speech molla_publication Question answering on speech transcripts (QAst) is a pilot track of the CLEF competition. In this paper we present our contribution to QAst, which is centred on a study of Named Entity (NE) recognition on speech transcripts, and how it impacts on the accuracy of the final question answering system. We have ported AFNER, the NE recogniser of the AnswerFinder question-answering project, to the set of answer types expected in the QAst track. AFNER uses a combination of regular expressions, lists of names (gazetteers) and machine learning to find NeWS in the data. The machine learning component was trained on a development set of the AMI corpus. In the process we identified various problems with scalability of the system and the existence of errors of the extracted annotation, which lead to relatively poor performance in general. Performance was yet comparable with state of the art, and the system was second (out of three participants) in one of the QAst subtasks.http://www.bibsonomy.org/bibtex/2753c74267baabe14fe6d420b78043998/diego_madiego_ma2007-12-14T02:48:42+01:00named_entities machine_learning <span style="color:#555555;">GuoDong <a href="http://www.bibsonomy.org/author/Zhou">Zhou</a> and Jian <a href="http://www.bibsonomy.org/author/Su">Su</a> </span><em>Proc. 40th Annual Meeting of the Association for Computational Linguistics ACL 2002, </em>(<em>2002</em>)Fri Dec 14 02:48:42 CET 2007Proc. 40th Annual Meeting of the Association for Computational Linguistics (ACL 2002)Named Entity Recognition using an {HMM}-based Chunk Tagger2002named_entities machine_learning This paper proposes a Hidden Markov Model (HMM) and an HMM-based chunk tagger, from which a named entity (NE) recognition (NER) system is built to recognize and classify names, times and numerical quantities. Through the HMM, our system is able to apply and integrate four types of internal and external evidences: 1) simple deterministic internal feature of the words, such as capitalization and digitalization; 2) internal semantic feature of important triggers; 3) internal gazetteer feature; 4) external macro context feature. In this way, the NER problem can be resolved effectively. Evaluation of our system on MUC-6 and MUC-7 English NE tasks achieves F-measures of 96.6% and 94.1% respectively. It shows that the performance is significantly better than reported by any other machine-learning system. Moreover, the performance is even consistently better than those based on handcrafted rules.http://www.bibsonomy.org/bibtex/22b0790ca9fa1c810363f5df441fc1254/diego_madiego_ma2007-12-14T02:47:08+01:00named_entities speech <span style="color:#555555;">Mihai <a href="http://www.bibsonomy.org/author/Surdeanu">Surdeanu</a> and Jordi <a href="http://www.bibsonomy.org/author/Turmo">Turmo</a> and Eli <a href="http://www.bibsonomy.org/author/Comelles">Comelles</a> </span><em>Proceedings Interspeech-05, </em><em>Lisbon, </em>(<em>2005</em>)Fri Dec 14 02:47:08 CET 2007LisbonProceedings Interspeech-05Named Entity Recognition from Spontaneous Open-Domain Speech2005named_entities speech This paper presents an analysis of named entity recognition and classification in spontaneous speech transcripts. We annotated a significant fraction of the Switchboard corpus with six named entity classes and investigated a battery of machine learning models that include lexical, syntactic, and semantic attributes. The best recognition and classification model obtains promising results, approaching within 5% a system evaluated on clean textual data.http://www.bibsonomy.org/bibtex/28a56675983754175b10280cc944d8e92/diego_madiego_ma2007-12-14T02:44:32+01:00question_answering named_entities <span style="color:#555555;">Elisa <a href="http://www.bibsonomy.org/author/Noguera">Noguera</a> and Antonio <a href="http://www.bibsonomy.org/author/Toral">Toral</a> and Fernando <a href="http://www.bibsonomy.org/author/Llopis">Llopis</a> and Rafael <a href="http://www.bibsonomy.org/author/Mu{\~n}oz">Mu&#241;oz</a> </span><em>Proceedings of the 8th International Conference on Text, Speech \&amp; Dialogue, </em><em>page 428-434. </em>(<em>2005</em>)Fri Dec 14 02:44:32 CET 2007Proceedings of the 8th International Conference on Text, Speech \& Dialogue428-434Reducing Question Answering Input Data Using Named Entity Recognition2005question_answering named_entities In a previous paper we proved that Named Entity Recognition plays an important role to improve Question Answering by both increasing the quality of the data and by reducing its quantity. Here we present a more in-depth discussion, studying several ways in which NER can be applied in order to produce a maximum data reduction. We achieve a 60% reduction without significant data loss and a 92.5% with a reasonable implication in data quality.http://www.bibsonomy.org/bibtex/222f9837dac4a70418136ddfff25b241d/diego_madiego_ma2007-12-14T02:44:29+01:00named_entities question_answering speech <span style="color:#555555;">Cheng <a href="http://www.bibsonomy.org/author/Niu">Niu</a> and Wei <a href="http://www.bibsonomy.org/author/Li">Li</a> and <a href="http://www.bibsonomy.org/author/Jihong">Jihong</a> and Rohini <a href="http://www.bibsonomy.org/author/Shrihari">Shrihari</a> </span><em>International Journal on Artificial Intelligence Tools</em><em>13(1):141-156</em>(<em>2004</em>)Fri Dec 14 02:44:29 CET 2007International Journal on Artificial Intelligence Tools1141-156Orthographic Case Restoration Using Supervised Learning without Manual Annotation132004named_entities question_answering speech One challenge in text processing is the treatment of case insensitive documents such as speech recognition results. The traditional approach is to re-train a language model excluding case-related features. This paper presents an alternative two-step approach whereby a preprocessing module (Step 1) is designed to restore case-sensitive form which is subsequently processed by the original system (Step 2). Step 1 is mainly implemented as a Hidden Markov Model trained on a large raw corpus of case sensitive documents. It is demonstrated that this approach (i) outperforms the feature exclusion approach for named entity tagging, (ii) leads to limited degradation for parsing, relationship extraction and case insensitive question answering, (iii) reduces system complexity, and (iv) has wide applicability: the restored text can be used in both statistical model and rule-based systems.http://www.bibsonomy.org/bibtex/2cf5005cce6fad851c7227451f85c4fcb/diego_madiego_ma2007-12-14T02:43:23+01:00named_entities <span style="color:#555555;">Andrei <a href="http://www.bibsonomy.org/author/Mikheev">Mikheev</a> and Marc <a href="http://www.bibsonomy.org/author/Moens">Moens</a> and Claire <a href="http://www.bibsonomy.org/author/Grover">Grover</a> </span><em>Proceedings of the Association for Computational Linguistics, </em><em>page 1--8. </em><em>Association for Computational Linguistics, </em>(<em>1999</em>)Fri Dec 14 02:43:23 CET 2007Proceedings of the Association for Computational Linguistics1--8Named Entity recognition without gazetteers1999named_entities http://www.bibsonomy.org/bibtex/2f9d2c45fe747b42f22f5da88cf71fd41/diego_madiego_ma2007-12-14T02:40:53+01:00inf_extraction named_entities <span style="color:#555555;">Kevin <a href="http://www.bibsonomy.org/author/Humphreys">Humphreys</a> and George <a href="http://www.bibsonomy.org/author/Demetriou">Demetriou</a> and Robert <a href="http://www.bibsonomy.org/author/Gaizauskas">Gaizauskas</a> </span><em>Proceedings of the Pacific Symposium on Biocomputing' 00 PSB'00, </em><em>page 502-513. </em><em>Honolulu, Hawaii, </em>(<em>2000</em>)Fri Dec 14 02:40:53 CET 2007Proceedings of the Pacific Symposium on Biocomputing' 00 (PSB'00)502-513Two Applications of Information Extraction to Biological Science Journal Articles: Enzyme Interactions and Protein Structures2000inf_extraction named_entities Information extraction technology, as defined and developed through the U.S. DARPA Message Understanding Conferences (MUCs), has proved successful at extracting information primarily from newswire texts and primarily in domains concerned with human activity. In this paper we consider the application of this technology to the extraction of information from scientific journal papers in the area of molecular biology. In particular, we describe how an information extraction system designed to participate in the MUC exercises has been modified for two bioinformatics applications: EMPathIE, concerned with enzyme and metabolic pathways; and PASTA, concerned with protein structure. Progress to date provides convincing grounds for believing that IE techniques will deliver novel and effective ways for scientists to make use of the core literature which defines their disciplines.http://www.bibsonomy.org/bibtex/2fe587667402ffc32b6d0d635db627a7d/diego_madiego_ma2007-12-14T02:39:12+01:00named_entities <span style="color:#555555;">Anthony F. <a href="http://www.bibsonomy.org/author/Gallippi">Gallippi</a> </span><em>Proc. COLING 1996, </em><em>page 424-429. </em>(<em>1996</em>)Fri Dec 14 02:39:12 CET 2007Proc. COLING 1996424-429Learning to Recognize Names Across Languages1996named_entities The development of natural language proccessing (NLP) systems that perform machine translation (MT) and information retrieval (IR) has highlighted the need for the automatic recognition of proper names. While various name recognizers have been developed, they suffer from being too limited; some only recognize one name class, and all are language specific. This work develops an approach to multilingual name recognition that allows a system optimized for one language to be ported to another with little additional effort and resources. An initial core set of linguistic features, useful for name recognition in most languages, is identified. When porting to a new language, these features need to be converted (partly by hand, partly by on-line lists), after which point machine learning (ML) techniques build decision trees that map features to name classes. A system initially optimized for English has been successfully ported to Spanish and Japanese. Only a few days of human effort for each new language results in performance levels comparable to that of the best current English systems.http://www.bibsonomy.org/bibtex/2a97c64b39d5d713400082f785d734d5b/diego_madiego_ma2007-12-14T02:38:51+01:00machine_learning named_entities <span style="color:#555555;">Michael <a href="http://www.bibsonomy.org/author/Fleischman">Fleischman</a> and Eduard <a href="http://www.bibsonomy.org/author/Hovy">Hovy</a> </span><em>Proceedings of Coling 2002, </em><em>Taipei, Taiwan, </em>(<em>2002</em>)Fri Dec 14 02:38:51 CET 2007Taipei, TaiwanProceedings of Coling 2002Fine Grained Classification of Named Entities2002machine_learning named_entities While Named Entity extraction is useful in many natural language applications, the coarse categories that most NE extractors work with prove insufficient for complex applications such as Question Answering and Ontology generation. We examine one coarse category of named entities, persons, and describe a method for automatically classifying person instances into eight finergrained subcategories. We present a supervised learning method that considers the local context surrounding the entity as well as more global semantic information derived from topic signatures and WordNet. We reinforce this method with an algorithm that takes advantage of the presence of entities in multiple contexts.http://www.bibsonomy.org/bibtex/2d4f233fd44172dfcf0d98dd03bc781e1/diego_madiego_ma2007-12-14T02:37:20+01:00named_entities machine_learning <span style="color:#555555;">Haoi Leong <a href="http://www.bibsonomy.org/author/Chieu">Chieu</a> and Hwee Tou <a href="http://www.bibsonomy.org/author/Ng">Ng</a> </span><em>Proceedings COLING 2002, </em>(<em>2002</em>)Fri Dec 14 02:37:20 CET 2007Proceedings COLING 2002Named Entity Recognition: A Maximum Entropy Approach Using Global Information2002named_entities machine_learning This paper presents a maximum entropy-based named entity recognizer (NER). It differs from previous machine learning-based NERs in that it uses information from the whole document to classify each word, with just one classifier. Previous work that involves the gathering of information from the whole document often uses a secondary classifier, which corrects the mistakes of a primary sentencebased classifier. In this paper, we show that the maximum entropy framework is able to make use of global information directly, and achieves performance that is comparable to the best previous machine learning-based NERs on MUC-6 and MUC-7 test data.http://www.bibsonomy.org/bibtex/2ce8cc5153963e37fc34d9b71c2bbcc93/diego_madiego_ma2007-12-14T02:35:36+01:00named_entities text_categorisation <span style="color:#555555;">Quintin <a href="http://www.bibsonomy.org/author/Armour">Armour</a> and Nathalie <a href="http://www.bibsonomy.org/author/Japkowicz">Japkowicz</a> and Stan <a href="http://www.bibsonomy.org/author/Matwin">Matwin</a> </span><em>Proceedings CLiNE 2005, </em><em>Gatineau, Canada, </em>(<em>2005</em>)Fri Dec 14 02:35:36 CET 2007Gatineau, CanadaProceedings CLiNE 2005The Role of Named Entities in Text Classification2005named_entities text_categorisation Named entities are typically associated with names of people, places and organizations and constitute a group of textual elements present in almost any type of document. The general techniques used to extract them and their variable-length property also makes them an attractive type of attribute to study in text classification. In this paper, several data sets are characterized as being either dependent or independent of named entities with a Naive Bayes based ranking technique. Using this characterization, results are presented which find named entities to be in fact useful in classification tasks, and that accuracy can be improved by considering them as a special type of attribute. Namely, the inclusion of regular terms, named entity representation and the frequency with which a classifier is retrained all have an impact on the classification of documents where named entities are important.