16,996 Hits in 3.5 sec

Cross-Language Retrieval with Wikipedia [chapter]

Péter Schönhofen, András Benczúr, István Bíró, Károly Csalogány
Lecture Notes in Computer Science  
We describe a method which is able to translate queries extended by narrative information from one language to another, with help of an appropriate machine readable dictionary and the Wikipedia on-line  ...  Another related eld is language modeling (an excellent overview is provided by [12] ), and applying language modeling to machine translation [4, 6] or information retrieval [7] is not new.  ...  The last related area is cross-language information retrieval itself (see for instance [22] for an overview).  ... 
doi:10.1007/978-3-540-85760-0_9 fatcat:sczlfqghgngj3emz74fgrtnefe

Exploiting Wikipedia API for Hindi-english Cross-language Information Retrieval

Vijay Kumar Sharma, Namita Mittal
2016 Procedia Computer Science  
Cross-Language Information Retrieval (CLIR) provides a solution for that language barrier which allows a user to ask a query in the native language and get the relevant documents in the different language  ...  Wikipedia title and inter-wiki link features are exploited for query translation. Target language documents are retrieved using vector space retrieval model and BM25 retrieval algorithm.  ...  Result analysis of Fire 2010 and Fire 2011 dataset for mono-lingual and cross-lingual retrieval with vector space model presented in Fig. 2 and Fig. 3 .  ... 
doi:10.1016/j.procs.2016.06.094 fatcat:n6ojd2ubvra3hh4nia6u5ezjhm

Employing Wikipedia's Natural Intelligence For Cross Language Information Retrieval [article]

Mikhail Basilyan
2009 arXiv   pre-print
We use this technique in combination with existing traditional Cross Language Information Retrieval (CLIR) techniques to improve their results.  ...  In this paper we present a novel method for retrieving information in languages other than that of the query.  ...  Cross Language Information Retrieval Cross Language Information Retrieval (CLIR) is the process of retrieving documents in a language or languages other than that of the original query.  ... 
arXiv:0906.2835v1 fatcat:ym2bozmtefhzvbhtar2pdv5axm

Explicit Versus Latent Concept Models for Cross-Language Information Retrieval

Philipp Cimiano, Antje Schultz, Sergej Sizov, Philipp Sorg, Steffen Staab
2009 International Joint Conference on Artificial Intelligence  
In this paper we investigate this question closer in the context of a cross-language setting, which inherently requires concept-based retrieval bridging between different languages.  ...  The field of information retrieval and text manipulation (classification, clustering) still strives for models allowing semantic information to be folded in to improve performance with respect to standard  ...  For mate retrieval evaluation, a text corpus with parallel documents in different languages is used.  ... 
dblp:conf/ijcai/CimianoSSSS09 fatcat:2tvikjbqlje65jq2g2ri2ohmge

Combining Query Translation Techniques to Improve Cross-Language Information Retrieval [chapter]

Benjamin Herbert, György Szarvas, Iryna Gurevych
2011 Lecture Notes in Computer Science  
In this paper we address the combination of query translation approaches for cross-language information retrieval (CLIR).  ...  We translate queries with Google Translate and extend them with new translations obtained by mapping noun phrases in the query to concepts in the target language using Wikipedia.  ...  Wikipedia based concept mapping. Wikipedia provides a natural source of multilingual information, with redirects and cross-language links between articles in different languages.  ... 
doi:10.1007/978-3-642-20161-5_77 fatcat:k2yqgrk6vfbcxn5i75rcvvx5yu

Interlinking Cross Language Metadata Using Heterogeneous Graphs and Wikipedia

Xiaozhong Liu, Miao Chen, Jian Qin
2014 International Conference on Dublin Core and Metadata Applications  
This paper addresses these problems by proposing a Cross-Language Metadata Network (CLMN) approach, which uses Wikipedia as the intermediary for cross-language metadata linking.  ...  construct cross-language metadata vocabulary.  ...  Potthast et al. (2008) used cross-language links in Wikipedia for cross-language information retrieval and showed a reasonably good performance in cross-language ranking and bi-lingual correlation ranking  ... 
dblp:conf/dc/LiuCQ14 fatcat:fcnfwmepmrf3nj6i4f25fn7fdq

Cross-language Semantic Matching for Discovering Links to e-gov Services in the LOD Cloud

Fedelucio Narducci, Matteo Palmonari, Giovanni Semeraro
2013 Extended Semantic Web Conference  
In this paper we present CroSeR (Cross-language Service Retriever), a tool able to match and retrieve cross-language e-gov services stored in the LOD cloud.  ...  We adopted a Wikipedia-based semantic representation in order to overcome the problems related to match really short textual descriptions associated to the services.  ...  Wikipedia Miner. Wikipedia Miner is a tool for automatically cross-referencing documents with Wikipedia [12] .  ... 
dblp:conf/esws/NarducciPS13 fatcat:ml6prz7yyrggxgzmeihvbarxai

Saarland University Spoken Language Systems Group at TAC KBP 2011

Fang Xu, Stefan Kazalski, Grzegorz Chrupala, Benjamin Roth, Xujian Zhao, Michael Wiegand, Dietrich Klakow
2011 Text Analysis Conference  
We mainly focus on developing a new system for the cross-language entity linking task. We compare the performance of monolingual retrieval and cross-lingual retrieval for entity linking.  ...  For NIL entity clustering, we group retrieved documents into reference clusters and assign NIL entities to a cluster by calculating the similarity between its document and each cluster.  ...  Document and query processing with natural language processing tools; 2. Document retrieval, to retrieve relevant articles with query expansion from the whole Wikipedia page archive; 3.  ... 
dblp:conf/tac/XuKCRZWK11 fatcat:55rvp273lrbyhf4xhvf4eioe7q

Cross-Language Semantic Retrieval and Linking of E-Gov Services [chapter]

Fedelucio Narducci, Matteo Palmonari, Giovanni Semeraro
2013 Lecture Notes in Computer Science  
The web application presented in this paper is named CroSeR (Cross-language Service Retriever) and supports public bodies in the process of linking their own service catalogs to the lod cloud.  ...  CroSeR supports different European languages and adopts a semantic representation of e-gov services based on Wikipedia.  ...  -Wikipedia Miner. Wikipedia Miner is a tool for automatically cross- referencing documents with Wikipedia [13] .  ... 
doi:10.1007/978-3-642-41338-4_9 fatcat:s7arnkeoi5b4vgqy22k4swhtgu

WikiTranslate: Query Translation for Cross-Lingual Information Retrieval Using Only Wikipedia [chapter]

Dong Nguyen, Arnold Overwijk, Claudia Hauff, Dolf R. B. Trieschnigg, Djoerd Hiemstra, Franciska de Jong
2009 Lecture Notes in Computer Science  
This paper presents WikiTranslate, a system which performs query translation for cross-lingual information retrieval (CLIR) using only Wikipedia to obtain translations.  ...  Queries are mapped to Wikipedia concepts and the corresponding translations of these concepts in the target language are used to create the final query.  ...  WikiTranslate will map the query to Wikipedia concepts. Through the cross-lingual links translations of the concepts into language-specific terms are retrieved.  ... 
doi:10.1007/978-3-642-04447-2_6 fatcat:7u6z45uywffdxakv7whsumxlaa

XOR QA: Cross-lingual Open-Retrieval Question Answering [article]

Akari Asai, Jungo Kasai, Jonathan H. Clark, Kenton Lee, Eunsol Choi, Hannaneh Hajishirzi
2021 arXiv   pre-print
This work extends open-retrieval question answering to a cross-lingual setting enabling questions from one language to be answered via answer content from another language.  ...  We establish baselines with state-of-the-art machine translation systems and cross-lingual pretrained models.  ...  XOR-TYDI QA is constructed with an annotation pipeline that allows for cross-lingual retrieval from large-scale Wikipedia corpora ( §2).  ... 
arXiv:2010.11856v3 fatcat:7mujquejk5fxxmhggc22plic7u

WikiUMLS: Aligning UMLS to Wikipedia via Cross-lingual Neural Ranking [article]

Afshin Rahimi and Timothy Baldwin and Karin Verspoor
2020 arXiv   pre-print
We propose a cross-lingual neural reranking model to match a UMLS concept with a Wikipedia page, which achieves a recall@1 of 72%, a substantial improvement of 20% over word- and char-level BM25, enabling  ...  We present our work on aligning the Unified Medical Language System (UMLS) to Wikipedia, to facilitate manual alignment of the two resources.  ...  If it is used for retrieval, many Wikipedia pages related to people with that name will rank high. However, if alias names of GERD in other languages (e.g.  ... 
arXiv:2005.01281v3 fatcat:nxbiiu4c6nevve3t25bmun3ibm

An Experimental Comparison of Explicit Semantic Analysis Implementations for Cross-Language Retrieval [chapter]

Philipp Sorg, Philipp Cimiano
2010 Lecture Notes in Computer Science  
mate retrieval task of between 62% (Multext) and 237% (JRC-ACQUIS) with respect to the original ESA model).  ...  The ESA model has been also recently extended to cross-lingual retrieval settings, which can be considered as an extreme case of the vocabulary mismatch problem.  ...  ESA has been also applied with reasonable success to information retrieval settings [3] , in particular cross-language retrieval settings [9, 8] .  ... 
doi:10.1007/978-3-642-12550-8_4 fatcat:ex4qez7m5rfkhebpnojxks2jzi

Mining Cross-Lingual/Cross-Cultural Differences in Concerns and Opinions in Blogs [chapter]

Hiroyuki Nakasaki, Mariko Kawaba, Takehito Utsuro, Tomohiro Fukuhara
2009 Lecture Notes in Computer Science  
Multilingual queries for retrieving blog feeds are created from Wikipedia entries.  ...  The goal of this paper is to cross-lingually analyze multilingual blogs collected with a topic keyword.  ...  queries for retrieving blog feeds are created from Wikipedia entries.  ... 
doi:10.1007/978-3-642-00831-3_20 fatcat:n2a3wzl2dbcsbpymi3y2c2tpf4

Using Wikipedia and Wiktionary in Domain-Specific Information Retrieval [chapter]

Christof Müller, Iryna Gurevych
2009 Lecture Notes in Computer Science  
For SR-Text, we alternatively perform the translation process by using cross-language links in Wikipedia, whereby the terms are directly mapped to concept vectors in the target language.  ...  While Wikipedia has already been used in IR, the application of Wiktionary in this task is new. We evaluate two retrieval models, i.e.  ...  The English language version of Wikipedia is by far the largest with almost 2.4 million articles, followed by the German language version with 754,000 articles.  ... 
doi:10.1007/978-3-642-04447-2_28 fatcat:vgxyj7euc5gg3jox5ulcbglboa
« Previous Showing results 1 — 15 out of 16,996 results