Filters








716 Hits in 4.7 sec

HITS at TAC KBP 2015: Entity Discovery and Linking, and Event Nugget Detection

Benjamin Heinzerling, Alex Judea, Michael Strube
2015 Text Analysis Conference  
Out of the eight systems that participated in the monolingual English EDL evaluation, our system is ranked first in linking and second in clustering.  ...  Our EDL system introduces a novel, interleaved multitasking approach, which allows interaction between interdependent entity linking subtasks while avoiding the structural and algorithmic complexity of  ...  Acknowledgments Benjamin Heinzerling has been supported by the German Research Foundation as part of the Research Training Group "Adaptive Preparation of Information from Heterogeneous Sources" (AIPHES  ... 
dblp:conf/tac/HeinzerlingJS15 fatcat:dmbhpoow3fg33pwslzaw6nouuu

C3EL: A Joint Model for Cross-Document Co-Reference Resolution and Entity Linking

Sourav Dutta, Gerhard Weikum
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
KB features for already disambiguated mentions to improve CCR.  ...  Experimental results on two different corpora, news-centric and web-centric, demonstrate significant gains over state-of-the-art baselines for both CCR and NEL.  ...  For NEL ground-truth construction, we link the entities to their Wikipedia pages (using Freebase's "on the web" property).  ... 
doi:10.18653/v1/d15-1101 dblp:conf/emnlp/DuttaW15 fatcat:6wktdxvaljgwdguvfdfkjtqpu4

Discovering Entities with Just a Little Help from You

Jaspreet Singh, Johannes Hoffart, Avishek Anand
2016 Proceedings of the 25th ACM International on Conference on Information and Knowledge Management - CIKM '16  
For popular entities, such a representation can be easily mined from Wikipedia, and many current entity disambiguation and linking methods make use of this fact.  ...  We propose novel human-in-the-loop retrieval methods for generating candidates based on gradient interleaving of diversification and textual relevance approaches.  ...  Effect of Rank 1 Owing to the 3 distinct classes of retrieval models, we find that each class selects a different document at rank 1.  ... 
doi:10.1145/2983323.2983798 dblp:conf/cikm/SinghHA16 fatcat:7ez2uvxvzjb4tjmes3ohvlh7du

Scalable and Distributed Methods for Entity Matching, Consolidation and Disambiguation Over Linked Data Corpora

Aidan Hogan, Antoine Zimmermann, JJrgen Umbrich, Axel Polleres, Stefan Decker
2012 Social Science Research Network  
the feasibility of our methods at that scale, and giving insights into the quality of the results for real-world data.  ...  Our methods are based upon distributed sorts and scans of the corpus, where we deliberately avoid the requirement for indexing all data.  ...  We would also like to thank the anonymous reviewers and the editors for their time and valuable comments.  ... 
doi:10.2139/ssrn.3198933 fatcat:rkewnbi6rvbyzj4zbczjkb2y5u

Scalable and distributed methods for entity matching, consolidation and disambiguation over linked data corpora

Aidan Hogan, Antoine Zimmermann, Jürgen Umbrich, Axel Polleres, Stefan Decker
2012 Journal of Web Semantics  
the feasibility of our methods at that scale, and giving insights into the quality of the results for real-world data.  ...  Our methods are based upon distributed sorts and scans of the corpus, where we deliberately avoid the requirement for indexing all data.  ...  We would also like to thank the anonymous reviewers and the editors for their time and valuable comments.  ... 
doi:10.1016/j.websem.2011.11.002 fatcat:gekxu2bqarbt5h2mkbtpedbj5m

Little Knowledge Rules the Web: Domain-Centric Result Page Extraction [chapter]

Tim Furche, Georg Gottlob, Giovanni Grasso, Giorgio Orsi, Christian Schallhart, Cheng Wang
2011 Lecture Notes in Computer Science  
It models domain knowledge about (1) records and attributes of the domain, (2) low-level (textual) representations of these concepts, and (3) constraints linking representations to records and attributes  ...  These approaches trade intensive user interaction for precision.  ...  Figure 3 shows the identified clusters for the Zoopla case: one rooted at D 2 for featured properties, one at D 3 for standard properties.  ... 
doi:10.1007/978-3-642-23580-1_6 fatcat:zbiw2t5egbh5rffjwfpob623a4

Namesake alias mining on the Web and its role towards suspect tracking

Tarique Anwar, Muhammad Abulaish
2014 Information Sciences  
The retrieved webpages are modeled into a graph, and a clustering algorithm is applied to disambiguate the webpages.  ...  Additionally the contribution includes the disambiguation technique that doesn't need to have a pre-determined number of clusters to be generated and the light-weight text pattern based alias mining technique  ...  The authors would also like to thank King Abdulaziz City for Science and Technology (KACST) and King Saud University for their support.  ... 
doi:10.1016/j.ins.2014.02.050 fatcat:zxpiwkl2nzeszosiznijymvsrq

Event abstraction in process mining: literature review and taxonomy

Sebastiaan J. van Zelst, Felix Mannhardt, Massimiliano de Leoni, Agnes Koschmider
2020 Granular Computing  
Most process mining techniques assume that the event data are of the same and/or appropriate level of granularity.  ...  Analyzing event data, i.e., the focus of process mining, yields a detailed understanding of the process, e.g., we are able to discover the control flow of the process and detect compliance and performance  ...  as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.  ... 
doi:10.1007/s41066-020-00226-2 fatcat:vwmncatr4zdphhkve5e6kqnzoy

NLP-based Ontology Learning from Legal Texts. A Case Study

Alessandro Lenci, Simonetta Montemagni, Vito Pirrelli, Giulia Venturi
2007 International Conference on Artificial Intelligence and Law  
We use a fully-implemented ontology learning system (T2K) that includes a battery of tools for Natural Language Processing (NLP), statistical text analysis and machine language learning.  ...  Evaluated results, however preliminary, are very encouraging, showing the great potential of NLP-powered incremental systems like T2K for accurate large-scale semi-automatic extraction of legal ontologies  ...  In fact, of all verb-term pairs attested in the corpus only a subset of highly salient such pairs is considered for clustering by CLASS.  ... 
dblp:conf/icail/LenciMPV07 fatcat:n64upo7ej5dv7cmfrt7yhmojxi

The LIC2M's CLEF 2003 System

Romaric Besançon, Gaël de Chalendar, Olivier Ferret, Christian Fluhr, Olivier Mesnard, Hubert Naets
2003 Conference and Labs of the Evaluation Forum  
For its first birthday, the LIC2M has participated to the Small Multilingual Track of CLEF 2003.  ...  Our system is based on a deep linguistic analysis of documents and queries and on an original search algorithm inherited from the Spirit (EMIR) system.  ...  The positional properties of this large set of categories (137 for French, 120 for English, 100 for Spanish and currently only 38 for German) will allow a very effective disambiguation, as we will see  ... 
dblp:conf/clef/BesanconCFFMN03a fatcat:fvk7xiz5cvhxbdmyeie5b2uto4

Recent Advances in LoRa: A Comprehensive Survey

Zehua Sun, Huanqi Yang, Kai Liu, Zhimeng Yin, Zhenjiang Li, Weitao Xu
2022 ACM transactions on sensor networks  
The vast demand for diverse applications raises new networking challenges, which have encouraged the development of a new paradigm of Internet of Things (IoT), e.g., LoRa.  ...  LoRa is a proprietary spread spectrum modulation technique, which provides a solution for long-range and ultra-low power-consumption transmission.  ...  Additionally, LoRaWAN deines three types of operation classes for end devices, i.e., class A(ll), B(eacon), and C(ontinue).  ... 
doi:10.1145/3543856 fatcat:n454idfkmnfk5fzgaau2goy3hm

Matching of events and activities

Thomas Baier, Andreas Rogge-Solti, Jan Mendling, Mathias Weske
2015 Proceedings of the 30th Annual ACM Symposium on Applied Computing - SAC '15  
Mapping the recorded events to activities of a given process model is essential for conformance checking, annotation and understanding of process discovery results.  ...  -August 2015 Thomas Baier: Matching events and activities, Preprocessing event logs for process analysis, © August 2015 Published online at the Institutional Repository of the University of Potsdam: URN  ...  They use the values of event attributes for the clustering of event instances, thus, integrating context data into their clustering approach.  ... 
doi:10.1145/2695664.2699491 dblp:conf/sac/0001RMW15 fatcat:76un2bqmzzd6np2dhnfiwztgt4

A scaffolding approach to coreference resolution integrating statistical and rule-based models

HEEYOUNG LEE, MIHAI SURDEANU, DAN JURAFSKY
2017 Natural Language Engineering  
Our approach combines many advantages: it incrementally builds clusters integrating joint information about entities, uses rules for deterministic phenomena, and integrates rich lexical, syntactic, and  ...  We describe a scaffolding approach to the task of coreference resolution that incrementally combines statistical classifiers, each designed for a particular mention type, with rule-based models (for sub-tasks  ...  From this data, for each mention, we extract at most one positive (coreferent) and possibly multiple negative (non-coreferent) training data points consisting of the pair of the corresponding mention and  ... 
doi:10.1017/s1351324917000109 fatcat:mg3iqfoopncftmk2bk4t3kduii

Zero-Shot Entity Linking by Reading Entity Descriptions

Lajanugen Logeswaran, Ming-Wei Chang, Kenton Lee, Kristina Toutanova, Jacob Devlin, Honglak Lee
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
We present the zero-shot entity linking task, where mentions must be linked to unseen entities without in-domain labeled data.  ...  The data and code are available at https: //github.com/lajanugen/zeshel. 1  ...  Acknowledgements We thank Rahul Gupta and William Cohen for providing detailed helpful feedback on an earlier draft of this paper.  ... 
doi:10.18653/v1/p19-1335 dblp:conf/acl/LogeswaranCLTDL19 fatcat:xaephiogvncorg6v56klsnoh5y

Semadrift: A Protégé Plugin For Measuring Semantic Drift In Ontologies

Thanos G. Stavropoulos, Stelios Andreadis, Efstratios Kontopoulos, Marina Riga, Panagiotis Mitzias, Ioannis Kompatsiaris
2017 Zenodo  
The paper presents the SemaDrift framework of tools and methods for measuring semantic drift across ontologies versions, which integrates currently investigated methods, such as text and structural similarity  ...  Released under Apache V2 License, the proposed framework developed in the context of PERICLES is available for download from http://mklab.iti.gr/project/semadrift-measure-semantic-drift-ontologies  ...  Thus, it can be easily perceived that semantic change can have drastic consequences on the use of ontologies in Semantic Web and Linked Data applications.  ... 
doi:10.5281/zenodo.345374 fatcat:ibfz6gshgre6xkcgvvj6fccwju
« Previous Showing results 1 — 15 out of 716 results