Filters








3,444 Hits in 3.2 sec

UTACLIR @ CLEF 2002: Towards a Unified Translation Process Model

Eija Airio, Heikki Keskustalo, Turid Hedlund, Ari Pirkola
2002 Conference and Labs of the Evaluation Forum  
This year we participated in CLEF with the new UTACLIR system, which is a single program unified for all the languages.  ...  The idea of UTACLIR is based on recognizing distinct source key types and processing them accordingly.  ...  Common features of bilingual and multilingual runs Handling of source words by ENGTWOL and the processing of source language stop words were similar in all the bilingual and multilingual runs we made,  ... 
dblp:conf/clef/AirioKHP02a fatcat:izn7n6novfeahfkgskl2nsw32i

The Effect of Cognates on Cognitive Control in Late Sequential Multilinguals: A Bilingual Advantage?

Jorik Fidler, Katja Lochtman
2019 Behavioral Sciences  
The results suggest the existence of a notification mechanism in the bilingual brain. This mechanism would notify the bilingual brain when dealing with cognates and orthographic neighbors.  ...  The question is whether or not cognate language processing affects cognitive control, resulting in a possible bilingual advantage.  ...  Acknowledgments: The authors thank Esli Struys of the Linguistics department at the Vrije Universiteit Brussel for his technical and methodological support of this research.  ... 
doi:10.3390/bs9030025 pmid:30857198 pmcid:PMC6466587 fatcat:srwmsbst5ngmpd3rnmg3pfqkjm

UB at CLEF 2005: Bilingual CLIR and Medical Image Retrieval Tasks [chapter]

Miguel E. Ruiz, Silvia B. Southwick
2006 Lecture Notes in Computer Science  
For the retrieval of medical images with multilingual annotations our main goal was to explore the combination of Content-Based Image Retrieval (CBIR) and text retrieval to retrieve medical images that  ...  We used a system that combines the content based image retrieval systems GIFT and the well known SMART system for text retrieval.  ...  Ruiz while he was working as a visiting researcher during the summer of 2005.  ... 
doi:10.1007/11878773_81 fatcat:pdztj32usjhjvoq5nvzy37yqzy

Experiments with the Eurospider Retrieval System for CLEF 2001 [chapter]

Martin Braschler, Bärbel Ripplinger, Peter Schäuble
2002 Lecture Notes in Computer Science  
We participated in the multilingual and monolingual tasks with three runs each. For our experiments, we investigated query translation using different approaches, as well as document translation.  ...  This paper describes the experiment setup that we used for our CLEF participation and gives a preliminary analysis of the results that were obtained.  ...  Additional thanks go to Patrick Frey for tuning the rules of the German stemmer and Min-Yen Kan for a lot of scripts originally written for last year's TREC that proved a big help in doing these experiments  ... 
doi:10.1007/3-540-45691-0_8 fatcat:kw3silxqirgq3pu7ctst3mtszy

Experiments with the Eurospider Retrieval System for CLEF 2000 [chapter]

Martin Braschler, Peter Scháuble
2001 Lecture Notes in Computer Science  
We participated in the multilingual and monolingual tasks with three runs each. For our experiments, we investigated query translation using different approaches, as well as document translation.  ...  This paper describes the experiment setup that we used for our CLEF participation and gives a preliminary analysis of the results that were obtained.  ...  Additional thanks go to Patrick Frey for tuning the rules of the German stemmer and Min-Yen Kan for a lot of scripts originally written for last year's TREC that proved a big help in doing these experiments  ... 
doi:10.1007/3-540-44645-1_13 fatcat:u6rze34hnravlkvckrkvaoxl4a

MIRACLE Approaches to Multilingual Information Retrieval: A Baseline for Future Research [chapter]

José L. Martínez, Julio Villena, Jorge Fombella, Ana G. Serrano, Paloma Martínez, Josê M. Goñi, José C. González
2004 Lecture Notes in Computer Science  
These experiments combine different basic techniques, linguistic-oriented and statistic-oriented, to be applied to the indexing and retrieval processes.  ...  This paper describes the first set of experiments defined by the MIRACLE (Multilingual Information RetrievAl for the CLEf campaign) research group for some of the cross language tasks defined by CLEF.  ...  Acknowledgements This work has been partially supported by the projects OmniPaper (European Union, 5th Framework Programme for Research and Technological Development, IST-2001-32174) and MIRACLE (Regional  ... 
doi:10.1007/978-3-540-30222-3_20 fatcat:7ahtzq364fe47khmowrohyubca

ISCAS at NTCIR-3: Monolingual, Bilingual and MultiLingual IR Tasks

Junlin Zhang, Le Sun, Weimin Qu, Lin Du, Yufang Sun, Yangxing Fan, Zhigen Lin
2002 NTCIR Conference on Evaluation of Information Access Technologies  
We use hybrid model integrating MT approach and dictionary-based approach in bilingual and multilingual subtasks.  ...  This paper reports the methods and procedures we took in the CLIR track of NTCIR3. In monolingual subtasks we mainly describe index representation and word segmentation method.  ...  Section 3, Section 4 and Section 5 describe the methods and procedures we took in Monolingual IR subtasks, Bilingual CLIR subtasks and Multilingual CLIR Subtasks respectively.  ... 
dblp:conf/ntcir/ZhangSQDSFL02 fatcat:ztvsklf7hbggdlx4d5y73xsdqi

Multilingual Training of Crosslingual Word Embeddings

Long Duong, Hiroshi Kanayama, Tengfei Ma, Steven Bird, Trevor Cohn
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers  
Most prior work constructs embeddings for a pair of languages, with English on one side.  ...  We investigate methods for building high quality crosslingual word embeddings for many languages in a unified vector space. In this way, we can exploit and combine information from many languages.  ...  We thank Yuta Tsuboi and Alvin Grissom II for helpful discussions, and Doris Hoogeveen for helping with the nl-es evaluation.  ... 
doi:10.18653/v1/e17-1084 dblp:conf/eacl/KanayamaCMBD17 fatcat:nspr7ochdndxjhafte4ctmxkua

Evaluation of MIRACLE Approach Results for CLEF 2003

José Luis Martínez-Fernández, Julio Villena-Román, Jorge Fombella, Ana García-Serrano, Alberto Ruiz-Cristina, Paloma Martínez, José M. Goñi, José Carlos González
2003 Conference and Labs of the Evaluation Forum  
This paper describes MIRACLE (Multilingual Information RetrievAl for the CLEf campaign) approach and results for the mono, bi and multilingual Cross Language Evaluation Forum tasks.  ...  The approach is based on the combination of linguistic and statistic techniques to perform indexing and retrieval tasks.  ...  Precision comparison with all runs submitted for the monolingual task  ... 
dblp:conf/clef/Martinez-FernandezVFGRMGG03 fatcat:h4kk2fzjwvdczh4trobwodh34a

Dictionary-Based Cross-Language Information Retrieval: Learning Experiences from CLEF 2000–2002

Turid Hedlund, Eija Airio, Heikki Keskustalo, Raija Lehtokangas, Ari Pirkola, Kalervo Järvelin
2004 Information retrieval (Boston)  
bilingual to multilingual.  ...  The development process of the UTACLIR query translation system will be regarded from the point of view of a learning process.  ...  The average precision of the additional multilingual run with the raw score approach was 0.1829, and with the Round Robin approach 0.1612.  ... 
doi:10.1023/b:inrt.0000009442.34054.55 fatcat:6mucmegfgnbgrbgfjhfq22hgzq

Linguistic (In) Equality, National Unity and Stability in Multilingual Commonwealth States: Cameroon's Experience

Gabsa Wilfred Nyongbet, Marie Mimesse Me Fame, Suh I Fru Norbert
2020 The International Journal of Humanities & Social Studies  
Official multilingual States may enjoy the envious reputation of being bilingual or multilingual as the case may be, but run the risk of political instability when all the languages are not treated justly  ...  In Cameroon, English and French are official languages with equal status.  ...  In multilingual States, language can act as a unifying factor depending on how the linguistic communities perceive and behave toward linguistic differences.  ... 
doi:10.24940/theijhss/2020/v8/i1/hs2001-035 fatcat:a7mhotvexfaudb722shr4imjl4

Multilingual Document Classification via Transductive Learning

Salvatore Romeo, Dino Ienco, Andrea Tagarelli
2015 Italian Information Retrieval Workshop  
any language translation process.  ...  A key aspect in our approach is the use of a large-scale multilingual knowledge base, BabelNet, to support the modeling of different language-written documents into a common conceptual space, without requiring  ...  We address the multilingual document classification problem from a different perspective. First, we are not restricted to deal with bilingual corpora dependent on machine translation.  ... 
dblp:conf/iir/RomeoIT15 fatcat:zt6re6bz2jejphavzvnxumftty

XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond [article]

Francesco Barbieri and Luis Espinosa Anke and Jose Camacho-Collados
2022 arXiv   pre-print
subsequently fine-tune on a target task; and (2) a set of unified sentiment analysis Twitter datasets in eight different languages and a XLM-T model fine-tuned on them.  ...  In this paper, we introduce XLM-T, a model to train and evaluate multilingual language models in Twitter.  ...  Jose Camacho-Collados is supported with a UKRI Future Leaders Fellowship.  ... 
arXiv:2104.12250v2 fatcat:a5t6l2ce4bdu5awq35wqmfawau

Low Cost Construction of a Multilingual Lexicon from Bilingual Lists

Lian Tze Lim, Bali Ranaivo-Malançon, Enya Kong Tang
2011 POLIBITS Research Journal on Computer Science and Computer Engineering With Applications  
We describe a low cost method for constructing a multilingual lexicon using only simple lists of bilingual translation mappings.  ...  Although there have been many efforts at (semi-)automatically merging bilingual machine readable dictionaries to produce a multilingual lexicon, most of these approaches place quite specific requirements  ...  We thank the evaluators who participated in the results evaluation, and the two anonymous reviewers for their comments on improving this paper.  ... 
doi:10.17562/pb-43-6 fatcat:dlltx4eeufadrorznb6riw5l3a

Development of the Multilingual Semantic Annotation System

Scott Piao, Francesca Bianchi, Carmen Dayrell, Angela D'Egidio, Paul Rayson
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
We used a set of bilingual dictionaries and word lists for this purpose.  ...  This paper reports on our research to generate multilingual semantic lexical resources and develop multilingual semantic annotation software, which assigns each word in running text to a semantic category  ...  Yufang Qian and Dr. Richard Xiao for their contributions to our research.  ... 
doi:10.3115/v1/n15-1137 dblp:conf/naacl/PiaoBDDR15 fatcat:q23zmmwv5naulmrz7xw5t4kzm4
« Previous Showing results 1 — 15 out of 3,444 results