5,983 Hits in 5.3 sec

Multilingual Question/Answering: the DIOGENE System

Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
2001 Text Retrieval Conference  
The system is based on a rather standard architecture which includes three components for question processing, search and answer extraction.  ...  Linguistic processing strongly relies on MULTIWORDNET, an extended version of the English WORDNET.  ...  Multilinguality is a crucial aspect when the language of the search question and the language of the text collection are different.  ... 
dblp:conf/trec/MagniniNPT01 fatcat:7gyxezvjkzb5rl4qekuhmvbjty

Cultural Heritage in CLEF (CHiC) 2013 [chapter]

Vivien Petras, Toine Bogers, Elaine Toms, Mark Hall, Jacques Savoy, Piotr Malak, Adam Pawłowski, Nicola Ferro, Ivano Masiero
2013 Lecture Notes in Computer Science  
For the multilingual and Polish sub-tasks, more than 170,000 documents were assessed for relevance on a tertiary scale.  ...  The interactive task created a rich data set comprising of questionnaire of log data. Further analysis of the data is planned in the future.  ...  This work was supported by PROMISE (Participative Research Laboratory for Multimedia and Multilingual Information Systems Evaluation), Network of Excellence co-funded by the 7th Framework Program of the  ... 
doi:10.1007/978-3-642-40802-1_23 fatcat:k4wapyy5cvdhvcsj5mkl66xtqm

Named Entity Disambiguation for German News Articles

Andreas Lommatzsch, Danuta Ploch, Ernesto William De Luca, Sahin Albayrak
2010 Lernen, Wissen, Daten, Analysen  
Named entity disambiguation has become an important research area providing the basis for improving search engine precision and for enabling semantic search.  ...  On the one hand WordNet comprises a relative small number of named entities while on the other hand DBpedia provides only little context for named entities.  ...  However, along with the development of information extraction and search technologies, the categories used for NEs were extended.  ... 
dblp:conf/lwa/LommatzschPLA10 fatcat:5er76fburva5jbhjv5smdwyasm

A Multimodal Analytics Platform for Journalists Analyzing Large-Scale, Heterogeneous Multilingual, and Multimedia Content

Stefanos Vrochidis, Anastasia Moumtzidou, Ilias Gialampoukidis, Dimitris Liparas, Gerard Casamayor, Leo Wanner, Nicolaus Heise, Tilman Wagner, Andriy Bilous, Emmanuel Jamin, Boyan Simeonov, Vladimir Alexiev (+3 others)
2018 Frontiers in Robotics and AI  
Therefore, there is a need for unified access to multilingual and multicultural news story material, beyond the level of a nation, ensuring context-aware, spatiotemporal, and semantic interpretation, correlating  ...  The textual and multimedia content is semantically integrated and indexed using a common representation, to be accessible through a web-based search engine.  ...  On the left side of the results page, advanced search features are available (a field that supports hybrid search). Search can be done on full text, entities or both.  ... 
doi:10.3389/frobt.2018.00123 pmid:33501002 pmcid:PMC7805659 fatcat:lw73va4vrbaq5ir5ztc5caujnu

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  
The system retrieves information from news sites, aggregates them into events (event detection), and summarizes them by extracting semantic labels of its most relevant entities (event representation) in  ...  We present an online multilingual system for event detection and comprehension from media feeds.  ...  This allows the multilingual linkage across stories, semantic search, and the linkage to customer contents by matching entities.  ... 
doi:10.1007/978-3-030-30796-7_24 fatcat:ugmc2kek4zfmrio4zgtnmbgf4a

Guiding the Evolution of a Multilingual Ontology in a Concrete Setting [chapter]

Mauro Dragoni, Chiara Di Francescomarino, Chiara Ghidini, Julia Clemente, Salvador Sánchez Alonso
2013 Lecture Notes in Computer Science  
Evolving complex artifacts as multilingual ontologies is a difficult activity demanding for the involvement of different roles and for guidelines to drive and coordinate them.  ...  We present the methodology and the underlying tool that have been used in the context of the Organic.Lingua project for the collaborative evolution of the multilingual Organic Agriculture ontology.  ...  Table 1 . 1 Usage of MoKi by the team of experts for accomplishing the multilingual evolution task Expert Entity Entity Entity Entity Discussion Discussion Category Creation Update Deletion Translation  ... 
doi:10.1007/978-3-642-38288-8_41 fatcat:52zyu3q5vfcifkt2k7qi3djnc4

Interlinking English and Chinese RDF Data Using BabelNet

Tatiana Lesnikova, Jérôme David, Jérôme Euzenat
2015 Proceedings of the 2015 ACM Symposium on Document Engineering - DocEng '15  
Data interlinking is a difficult task particularly in a multilingual environment like the Web.  ...  The experiment demonstrates that TF*IDF with a minimum amount of preprocessing steps can bring high results.  ...  This work has been done as part of the research within the Lindicle 7 (12-IS02-0002) project in cooperation with the Tsinghua University, China.  ... 
doi:10.1145/2682571.2797089 dblp:conf/doceng/LesnikovaDE15 fatcat:p6etrngqivccdm34h6kenmtqf4

EASE: Entity-Aware Contrastive Learning of Sentence Embedding [article]

Sosuke Nishikawa, Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka, Isao Echizen
2022 arXiv   pre-print
The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong indicator of text semantics and thus should provide rich training signals for sentence embeddings; (2)  ...  We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities.  ...  We then collect pages with topic categories for each language and remove the pages with two or more topic categories.  ... 
arXiv:2205.04260v1 fatcat:kbav7weyi5ey3hqcw76aevw5ge

Stalker, A Multilingual Text Mining Search Engine for Open Source Intelligence

Federico Neri, Massimo Pettoni
2008 2008 12th International Conference Information Visualisation  
STALKER provides with a language independent search and dynamic classification features for a broad range of data collected from several sources in a number of culturally diverse languages.  ...  This paper describes a content enabling system that provides deep semantic search and information access to large quantities of distributed multimedia data for both experts and general public.  ...  assigned divided by total number of categories assigned): in our tests, they were 75% and 80% respectively.  ... 
doi:10.1109/iv.2008.9 dblp:conf/iv/NeriP08 fatcat:tjcmpifkbjg6pli3ydltdoa7qa

Chemnitz at the CHiC Evaluation Lab 2012: Creating an Xtrieval Module for Semantic Enrichment

Jens Kürsten, Thomas Wilhelm, Daniel Richter, Maximilian Eibl
2012 Conference and Labs of the Evaluation Forum  
At the core of the majority of these experiments lies a prototype implementation for semantic enrichment based on DBpedia.  ...  The results also indicate that automatic query expansion does not improve retrieval performance for the pilot lab test collection.  ...  The authors take sole responsibility for the contents of this publication.  ... 
dblp:conf/clef/KurstenWRE12 fatcat:gasbgafi3jf25jay53h5a77hgq

Collaboratively built semi-structured content and Artificial Intelligence: The story so far

Eduard Hovy, Roberto Navigli, Simone Paolo Ponzetto
2013 Artificial Intelligence  
Finally, we thank the Artificial Intelligence Journal Editors-in-Chief, Tony Cohn, Rina Dechter and Ray Perrault, for their continued support throughout the preparation of this special issue.  ...  Acknowledgements The last two authors gratefully acknowledge the support of the ERC Starting Grant MultiJEDI No. 259234.  ...  Evaluation of entity ranking systems has been conducted in the context of the INEX evaluation forum since 2006, using Wikipedia as the test collection [48, 47] .  ... 
doi:10.1016/j.artint.2012.10.002 fatcat:mwk5o254urb2dejsh7c224uu3q

Entity Summarization Based on Entity Grouping in Multilingual Projected Entity Space

Eun-kyung KIM, Key-Sun CHOI
2017 IEICE transactions on information and systems  
Entities are first grouped according to projected multilingual categories that provide the multi-angled semantics of each entity into a single entity space.  ...  However, many of those descriptions are not useful for identifying the underlying characteristics of their corresponding entities because semantically redundant facts or triples are included in the descriptions  ...  and Swedish editions) to project multilingual category information into a single space that provides the integrated multi-angled semantics of each entity.  ... 
doi:10.1587/transinf.2016edp7235 fatcat:kn5malghcbc3ppdhlsmxmt7uzu

Polish Language Processing Chains for Multilingual Information Systems [chapter]

Maciej Ogrodniczuk, Adam Przepiórkowski
2012 Lecture Notes in Computer Science  
The ATLAS project, started in March 2010, intends to create a multilingual language processing framework integrating the common set of linguistic tools for a group of European languages, among them Polish  ...  Inflectional characteristics of this language offers the possibility to comment on a few more advanced functions such as multiword unit lemmatisation, vital for real-life presentation of extracted phrases  ...  morphosyntactic categories), noun phrases (with semantic heads) and named entities.  ... 
doi:10.1007/978-3-642-31178-9_14 fatcat:usgfmya33jbo7mhl2eqxi6ld2y

Meerkat Mafia: Multilingual and Cross-Level Semantic Textual Similarity Systems

Abhay Kashyap, Lushan Han, Roberto Yus, Jennifer Sleeman, Taneeya Satyapanich, Sunil Gandhi, Tim Finin
2014 Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)  
We describe UMBC's systems developed for the SemEval 2014 tasks on Multilingual Semantic Textual Similarity (Task 10) and Cross-Level Semantic Similarity (Task 3).  ...  The system ranked first for the Phrase-Word subtask but was not included in the official results due to a late submission.  ...  Acknowledgements This research was supported by awards 1228198, 1250627 and 0910838 from the U.S. National Science Foundation.  ... 
doi:10.3115/v1/s14-2072 dblp:conf/semeval/KashyapHYSSGF14 fatcat:737e23s5ubf5lkkclym4swrfw4

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.  ...  processor that reformulates the query to suit the search (monolingual and multilingual reformulations); • a search engine that searches the indexes for the closest documents to the reformulated queries  ... 
dblp:conf/clef/BesanconCFFMN03a fatcat:fvk7xiz5cvhxbdmyeie5b2uto4
« Previous Showing results 1 — 15 out of 5,983 results