Filters








99 Hits in 3.0 sec

Leveraging interlingual classification to improve web search

Jagadeesh Jagarlamudi, Paul N. Bennett, Krysta M. Svore
2012 Proceedings of the 21st international conference companion on World Wide Web - WWW '12 Companion  
Specifically, we use interlingual classification to infer the search language query's intent using the assist language click-through data.  ...  In this paper we address the problem of improving accuracy of web search in a smaller, data-limited search market (search language) using behavioral data from a larger, datarich market (assist language  ...  In this paper, we address the problem of improving web search ranking in a relatively data-scarce search language (e.g., German or French) using data from an assisting language (e.g., English).  ... 
doi:10.1145/2187980.2188114 dblp:conf/www/JagarlamudiBS12 fatcat:vxofrdgsvbdyhix6csfyyi6q4y

SKOS and the Semantic Web: Knowledge Organization, Metadata, and Interoperability

Eric Robinson
2010 SOAR@USA: Scholarship and Open Access Repository  
The Simplified Knowledge Organization System (SKOS) is a Semantic Web framework, based on the Resource Description Framework (RDF) for thesauri, classification schemes, and simple ontologies.  ...  the rapidly expanding information environment of the Web.  ...  improve efficient information searching and retrieval.  ... 
doi:10.46409/sr.ojzh9684 fatcat:62g2pwy67bgcnhn5rkibxaytaq

New taxonomy of easy-to-understand access services

Rocío Bernabé
2020 MonTI. Monografías de Traducción e Interpretación  
The taxonomy uses Gottlieb's (2005) semiotically-based classification to define E2U access services within the landscape of Audiovisual translation and to classify them according to their semiotic identity  ...  as compared to the standard access services. 2020.  ...  This singularity provides leverage to enhance their cognitive accessibility when they are designed according to valid guidelines, such as WCAG as proposed by Johansson (2016) , and according to simplification  ... 
doi:10.6035/monti.2020.12.12 fatcat:5o5w2zeux5bplh36kjs4vfm37a

A faceted approach to reachability analysis of graph modelled collections

Serwah Sabetghadam, Mihai Lupu, Ralf Bierig, Andreas Rauber
2017 International Journal of Multimedia Information Retrieval  
We use our framework to leverage the combination of features of different modalities through our formulation of faceted search.  ...  This study highlights the effect of different facets and link types in improving reachability of relevant information objects.  ...  the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.  ... 
doi:10.1007/s13735-017-0145-8 pmid:30956928 pmcid:PMC6417456 fatcat:psbvulhqzfervggettvlabv2jm

Polylingual Wordnet [article]

Mihael Arcan and John McCrae and Paul Buitelaar
2019 arXiv   pre-print
For this reason we leverage existing translations of WordNet in other languages to identify contextual information for wordnet senses from a large set of generic parallel corpora.  ...  Our experiment shows a significant improvement over translation without any contextual information.  ...  A similar approach to the one proposed in this paper is that of [61] , where they show that using the interlingual index of WordNet with the help of parallel text can improve word sense disambiguation  ... 
arXiv:1903.01411v1 fatcat:k7rilkthk5gs3gpokv7avy4ay4

TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering [article]

Chao Zhang, Fangbo Tao, Xiusi Chen, Jiaming Shen, Meng Jiang, Brian Sadler, Michelle Vanni, Jiawei Han
2018 arXiv   pre-print
Taxonomy construction is not only a fundamental task for semantic analysis of text corpora, but also an important step for applications such as information filtering, recommendation, and Web search.  ...  To ensure the quality of the recursive process, it consists of: (1) an adaptive spherical clustering module for allocating terms to proper levels when splitting a coarse topic into fine-grained ones; (  ...  Taking 'information retrieval' as an example: (1) at level three, TaxoGen can successfully find major areas in information retrieval: retrieval effectiveness, interlingual, Web search, rdf & xml query,  ... 
arXiv:1812.09551v1 fatcat:acch533pzjgeli7agbpkh6cpxa

Arabic Semantic Web Applications – A Survey

Aya M. Al-Zoghby, Ahmed Sharaf Eldin Ahmed, Taher T. Hamza
2013 Journal of Emerging Technologies in Web Intelligence  
Nevertheless, it is observable that the Arabic content on the Web is less than what should be. The evolution of the Semantic Web (SW) added a new dimension to this problem.  ...  This paper is an attempt to figure out the problem, its causes, and to open avenues to think about the solutions.  ...  Furthermore, the Ontologies are used to improve the Web search precision by searching for Web pages that hold certain concept instead of search using just keywords and ambiguous terminologies.  ... 
doi:10.4304/jetwi.5.1.52-69 fatcat:skcu5mm47bhadjsxqbttqtz4s4

Cross-lingual linking of multi-word entities and language-dependent learning of multi-word entity patterns [chapter]

Guillaume Jacquet, Maud Ehrmann, Jakub Piskorski, Hristo Tanev, Ralf Steinberger
2019 Zenodo  
Besides aiming at turning free text into semi-structured data for search and for machine-processing purposes, we use the system to link related news over time and across languages, as well as to detect  ...  When adding the new rules to the original rule-based NER system, F1 performance for Spanish increases from 42.4% to 50% (18% increase) and for English from 43.4% to 44.5% (2.5% in- crease).  ...  Users searching for such an entity will want to retrieve all mentions, independently of their spelling or abbreviation or language.  ... 
doi:10.5281/zenodo.2579048 fatcat:3cwcjk6z35bzxaiyxecgz5x2va

NLP commercialisation in the last 25 years

Robert Dale
2019 Natural Language Engineering  
The editorial preface to the first issue emphasised that the focus of the journal was to be on the practical application of natural language processing (NLP) technologies: the time was ripe for a serious  ...  publication that helped encourage research ideas to find their way into real products.  ...  NL search Conceptual search Machine translation Glossary look-up Translation memories and direct transfer Interlingual MT and computational power had increased to the extent that speech recognition  ... 
doi:10.1017/s1351324919000135 fatcat:7bfrwfaxwvaolcqv5snvl46dne

Multilinguality in the digital library

Anne R. Diekema
2012 Electronic library  
The researchers mine the Web by extracting translations from bilingual search results and by adding these translations to the multilingual dictionary.  ...  did not show improvement in retrieval results.  ... 
doi:10.1108/02640471211221313 fatcat:2i3fopnqwngadgytpve2tbqklq

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
We propose a joint learning model which combines pairwise classification and mention clustering with Markov logic.  ...  The model is not restricted to nominal  ...  in web search.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Using Foreign Inclusion Detection to Improve Parsing Performance

Beatrice Alex, Amit Dubey, Frank Keller
2007 Conference on Empirical Methods in Natural Language Processing  
We show this for English inclusions, which are sufficiently frequent to present a problem when parsing German.  ...  evaluation on the TIGER corpus shows that our inclusion entity model achieves a performance gain of 4.3 points in F-score over a baseline of no inclusion detection, and even outperforms a parser with access to  ...  We would also like to thank Claire Grover for her comments and feedback.  ... 
dblp:conf/emnlp/AlexDK07 fatcat:tabpugc4t5azdjp475gebibkqq

Cross-language information retrieval models based on latent topic models trained with document-aligned comparable corpora

Ivan Vulić, Wim De Smet, Marie-Francine Moens
2012 Information retrieval (Boston)  
The Bilingual Latent Dirichlet Allocation model (BiLDA) allows us to create an interlingual, language-independent representation of both queries and documents.  ...  We confirm these findings in an alternative evaluation, where we automatically generate queries and perform the known-item search on a test subset of Wikipedia articles.  ...  Acknowledgements We would like to thank the anonymous reviewers for their insightful and constructive comments.  ... 
doi:10.1007/s10791-012-9200-5 fatcat:ednqhlfih5dcphmyagg4hzz37i

A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classification [article]

Arijit Nag, Bidisha Samanta, Animesh Mukherjee, Niloy Ganguly, Soumen Chakrabarti
2021 arXiv   pre-print
Relation classification (sometimes called 'extraction') requires trustworthy datasets for fine-tuning large language models, as well as for evaluation.  ...  Despite recent interest in deep generative models for Indian languages, relation classification is still not well served by public data sets.  ...  To enforce data diversity, we further collect sentences from mixed sources, by querying the Google Web search engine API with (e 1 , e 2 ) and selecting the top five response URLs, 5 which are fetched.  ... 
arXiv:2110.09570v1 fatcat:dvkk6iet7jcfta2m5q53u35g7i

A Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs [article]

Alexander Kalinowski, Yuan An
2020 arXiv   pre-print
We provide a classification of the relevant alignment techniques and discuss benchmark datasets used in this field of research.  ...  Given the pervasive nature of these algorithms, the natural question becomes how to exploit the embedding spaces to map, or align, embeddings of different data sources.  ...  neighbor searches can then be executed to generate candidate pairs.  ... 
arXiv:2010.13688v1 fatcat:npkzwukih5gwnkvng2fxy7ls5y
« Previous Showing results 1 — 15 out of 99 results