2,727 Hits in 7.3 sec

Multilingual Story Link Detection Based on Event Term Weighting on Times and Multilingual Spaces [chapter]

Kyung-Soon Lee, Kyo Kageura
2004 Lecture Notes in Computer Science  
Our approach uses features such as timelines and multilingual spaces for giving distinctive weights to terms that constitute linguistic representation of events.  ...  In this paper, we propose a novel approach for multilingual story link detection.  ...  For multilingual story link detection, a machine translation system is used to make multilingual spaces to one language space. Terms are weighted based on event term properties.  ... 
doi:10.1007/978-3-540-30544-6_43 fatcat:cmcqy5apjfheraidq2vzbrbqo4

VLX-Stories: Building an Online Event Knowledge Base with Emerging Entity Detection [chapter]

Dèlia Fernàndez-Cañellas, Joan Espadaler, David Rodriguez, Blai Garolera, Gemma Canet, Aleix Colom, Joan Marco Rimmek, Xavier Giro-i-Nieto, Elisenda Bou, Juan Carlos Riveiro
2019 Lecture Notes in Computer Science  
We present an online multilingual system for event detection and comprehension from media feeds.  ...  At the same time, this external knowledge graph can also be extended with a Dynamic Entity Linking (DEL) module, which detects emerging entities (EE) on unstructured data.  ...  The extraction of mentions and its linkage to entities from an external multilingual KG generates an event linked space.  ... 
doi:10.1007/978-3-030-30796-7_24 fatcat:ugmc2kek4zfmrio4zgtnmbgf4a

An introduction to the Europe Media Monitor family of applications [article]

Ralf Steinberger, Bruno Pouliquen, Erik van der Goot
2013 arXiv   pre-print
Most large organizations have dedicated departments that monitor the media to keep up-to-date with relevant developments and to keep an eye on how they are represented in the news.  ...  We discuss design issues necessary to be able to achieve this high multilinguality, as well as the benefits of this multilinguality.  ...  EMM applications produce daily and long-term social networks of different types ( [17] , [22] ), based on weighted co-occurrence, based on labeled relations, and based on who mentions whom in reported  ... 
arXiv:1309.5290v1 fatcat:wpcgvkswkne7vbknmm23yhj3w4

Probabilistic topic modeling in multilingual settings: An overview of its methodology and applications

Ivan Vulić, Wim De Smet, Jie Tang, Marie-Francine Moens
2015 Information Processing & Management  
space of latent cross-lingual topics, that is, how to effectively employ learned per-topic word distributions and per-document topic distributions of any multilingual probabilistic topic model in various  ...  We provide clear directions for future research in the field by providing a systematic overview of how to link and transfer aspect knowledge across corpora written in different languages via the shared  ...  financed by the EU Sixth Framework Programme ICT, AMASS++ (SBO-060051) financed by Instituut voor de Aanmoediging van Innovatie door Wetenschap en Technologie in Vlaanderen (IWT), WebInsight (BIL/08/08), and  ... 
doi:10.1016/j.ipm.2014.08.003 fatcat:vpa5wdjc5ja5lchaoocctciqui


2003 Digital Media Processing for Multimedia Interactive Services  
Text processing tools operate on the text stream produced by the speech recogniser and perform named entity detection, term recognition, topic detection, and story segmentation.  ...  The retrieval engine is based on a weighted boolean model with intelligent indexing components.  ...  Story Detection and Topic Classification (SD/TC) Story detection (SD) and topic classification (TC) use a set of models trained on an annotated corpus of stories and their associated topics.  ... 
doi:10.1142/9789812704337_0102 fatcat:vjhi65k6x5d43drbjokwqze7r4

News Across Languages - Cross-Lingual Document Similarity and Event Tracking [article]

Jan Rupnik, Andrej Muhic, Gregor Leban, Primoz Skraba, Blaz Fortuna, Marko Grobelnik
2015 arXiv   pre-print
Taking a multilingual stream and clusters of articles from each language, we compare different cross-lingual document similarity measures based on Wikipedia.  ...  Significant events are reported by different sources and in different languages. In this work, we address the problem of tracking of events in a large multilingual stream.  ...  We do not address the problem of detection of events and instead base our evaluation on an online system for detection of world events, Event Registry.  ... 
arXiv:1512.07046v1 fatcat:5vbwcxioxbdqdbr6rbsf5dyeri

A Latent Semantic Indexing-based approach to multilingual document clustering

Chih-Ping Wei, Christopher C. Yang, Chia-Min Lin
2008 Decision Support Systems  
The empirical evaluation results show that the proposed LSI-based MLDC technique achieves satisfactory clustering effectiveness, measured by both cluster recall and cluster precision, and is capable of  ...  Motivated by the significance of this demand, this study designs a Latent Semantic Indexing (LSI)-based MLDC technique capable of generating knowledge maps (i.e., document clusters) from multilingual documents  ...  i, and x ji is the weight of term j in document i).  ... 
doi:10.1016/j.dss.2007.07.008 fatcat:dqy7qazebvb4bfw5hajlgmtmoe

Applying Dynamic Co-occurrence in Story Link Detection

Hua Zhao, Tiejun Zhao
2009 Journal of Computing and Information Technology  
Experimental results show that the story link detection systems based on the dynamic co-occurrence perform very well, which testifies the great capabilities of the dynamic co-occurrence.  ...  are about the same event, or linked.  ...  Story link detection is thought of as the basis for other event-based topic analysis tasks, such as topic tracking, topic detection, and first story detection [1] .  ... 
doi:10.2498/cit.1001104 fatcat:lytexmcaxbcfbmksrdf5brejwa

Using contextual analysis for news event detection

W. Lam, H. M. L. Meng, K. L. Wong, J. C. H. Yen
2001 International Journal of Intelligent Systems  
We propose a new approach to performing event detection from multilingual newswire stories.  ...  Concept terms of a story are derived from statistical context analysis between sentences in the news story and stories in the concept database.  ...  Our corpus consists of English and Chinese news. One issue for event detection is to deal with multilingual news content.  ... 
doi:10.1002/int.1022 fatcat:3rsspnjgp5a2rkww5slqes6j24

Navigating Multilingual News Collections Using Automatically Extracted Information

Ralf Steinberger, Bruno Pouliquen, Camelia Ignat
2005 Journal of Computing and Information Technology  
The fully functional prototype system allows users to explore and navigate multilingual document collections across languages and time.  ...  found, links clusters and entities, and generates hyperlinks.  ...  We furthermore thank the many persons who have contributed over time to develop the existing text analysis tool set and to adapt it to so many languages.  ... 
doi:10.2498/cit.2005.04.01 fatcat:z3tjpgtdzfa77auf6etjpxva7a

Mastering the Media Hype: Methods for Deduplication of Conflict Events from News Reports

Vanni Zavarella, Jakub Piskorski, Camelia Ignat, Hristo Tanev, Martin Atkinson
2020 International Joint Conference on Artificial Intelligence  
The first approach (Cluster Linking) consists of linking news article clusters across time, prior to event extraction, while the second one (Event Linking) is based on classification and aggregation of  ...  Machine coding of conflict event datasets has recently emerged as a time-effective method which can back up predictive models for conflict escalation at national and sub-national level.  ...  The first approach is based on linking clusters of news items, while the second one is based on classification and aggregation of related events.  ... 
dblp:conf/ijcai/ZavarellaPITA20 fatcat:lkcqbefup5hnvckmux2raahn5e

Overviewing Important Aspects of the Last Twenty Years of Research in Comparable Corpora [chapter]

Serge Sharoff, Reinhard Rapp, Pierre Zweigenbaum
2013 Building and Using Comparable Corpora  
It computes node-similarities between two graphs and allows for weighted graph edges. Garera et al. [36] use a vector space model but consider dependency links rather than word co-occurrences.  ...  In contrast to the dominating vector space approaches based on wordco-occurrence data, Michelbacher et al.  ... 
doi:10.1007/978-3-642-20128-8_1 fatcat:votpvm7donegrao4apmexvjbra

Story Link Detection Based on Event Words [chapter]

Letian Wang, Fang Li
2011 Lecture Notes in Computer Science  
In this paper, we propose an event words based method for story link detection.  ...  Different from previous studies, we use time and places to label nouns and named entities, the featured nouns/named entities are called event words.  ...  Acknowledgement The research is supported by the National Science Foundation of China under Grant No.60873134, Threads and topics detection for news events.  ... 
doi:10.1007/978-3-642-19437-5_16 fatcat:xizelyhnczgxfmfw72qs6fiui4

Multilingual Clustering of Streaming News

Sebastião Miranda, Arturs Znotins, Shay Cohen, Guntis Barzdins
2018 Zenodo  
To this end, we describe a novel method for clustering an incoming stream of multilingual documents into monolingual and crosslingual story clusters.  ...  Our method is simple to implement, computationally efficient and produces state-of-the-art results on datasets in German, English and Spanish.  ...  Acknowledgments We would like to thank Esma Balkır, Nikos Papasarantopoulos, Afonso Mendes, Shashi Narayan and the anonymous reviewers for their feedback.  ... 
doi:10.5281/zenodo.2359130 fatcat:755hbpgtmjdaddl2pkwl6x6hsq

Multilingual Clustering of Streaming News [article]

Sebastião Miranda, Artūrs Znotiņš, Shay B. Cohen, Guntis Barzdins
2018 arXiv   pre-print
To this end, we describe a novel method for clustering an incoming stream of multilingual documents into monolingual and crosslingual story clusters.  ...  Our method is simple to implement, computationally efficient and produces state-of-the-art results on datasets in German, English and Spanish.  ...  Acknowledgments We would like to thank Esma Balkır, Nikos Papasarantopoulos, Afonso Mendes, Shashi Narayan and the anonymous reviewers for their feedback.  ... 
arXiv:1809.00540v1 fatcat:rpp3zrwkzzcc3iqpzjbprq75e4
« Previous Showing results 1 — 15 out of 2,727 results