Filters








30,645 Hits in 9.0 sec

Construction of Corpus in Artificial Intelligence Age

Changchun Hong, Wen-Pei Sung, Tao-Yun Han
2018 MATEC Web of Conferences  
In this way, machine translation is improving in its scope and accuracy in translation with the goal to take up the tedious work of human translation as well as to increase the speed and reduce the cost  ...  The paper aims to exploring the mode of corpus construction from the perspective of information mining, information retrieval and information processing.  ...  At present, the main methods for cross-language retrieval are question-based translation methods, document translation methods, question-document translation methods, intermediate translation methods,  ... 
doi:10.1051/matecconf/201817503037 fatcat:7lfrc2hpxjhi3phgqaaejbgscy

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).  ...  For two CLIR collections, we show that the proposed model provides meaningful translations that improve the strong baseline CLIR model based on a top performing SMT system.  ...  Combination of statistical machine translation (SMT), machine readable dictionary (MRD) based models or similarity thesauri (ST) proved to be difficult [1] due to the difference in the accuracy of individual  ... 
doi:10.1007/978-3-642-20161-5_77 fatcat:k2yqgrk6vfbcxn5i75rcvvx5yu

Ice-tea

Dan Wu, Daqing He
2008 Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '08  
EXTENDED ABSTRACT In cross-language information retrieval (CLIR), relevance feedback (RF) has been demonstrated to be effective in improving retrieval results, especially when reliable RF information can  ...  It is developed to utilize the RF information from users to conduct TE, QE, and the integration of them to improve CLIR results. ICE-TEA performs query translation based CLIR.  ...  EXTENDED ABSTRACT In cross-language information retrieval (CLIR), relevance feedback (RF) has been demonstrated to be effective in improving retrieval results, especially when reliable RF information  ... 
doi:10.1145/1390334.1390556 dblp:conf/sigir/WuH08 fatcat:zxqsbis6lzbe3nujsvq5cje5qu

Pivot Through English: Reliably Answering Multilingual Questions without Document Retrieval [article]

Ivan Montero, Shayne Longpre, Ni Lao, Andrew J. Frank, Christopher DuBois
2021 arXiv   pre-print
They not only suffer from the shortcomings of non-English document retrieval, but are reliant on language-specific supervision for either the task or translation.  ...  Existing methods for open-retrieval question answering in lower resource languages (LRLs) lag significantly behind English.  ...  For this task we combine and compare state-ofthe-art methods in machine translation ("translate test") and cross-lingual semantic similarity, in order to map LRL queries to English, and then English answers  ... 
arXiv:2012.14094v2 fatcat:bbvne32bxvhixowjyq5fewpxre

A comparison of query translation methods for English-Japanese cross-language information retrieval (poster abstract)

Gareth Jones, Tetsuya Sakai, Nigel Collier, Akira Kumano, Kazuo Sumita
1999 Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '99  
In this paper we report results of an investigation into English-Japanese Cross-Language Information Retrieval (CLIR) comparing a number of query translation methods.  ...  Results from experiments using the standard BMIR-J2 Japanese collection suggest that full machine translation (MT) can outperform popular dictionary-based query translation methods and further that in  ...  Introduction Interest in Cross-Language Information Retrieval (CLIR) has grown rapidly in recent years [l] [2] [3] .  ... 
doi:10.1145/312624.312690 dblp:conf/sigir/JonesSCKS99 fatcat:etpfq67rcfcbtc6bb7xjtocfrm

Introduction to the Special Issue on Cross-Language Algorithms and Applications

Marta R. Costa-jussà, Srinivas Bangalore, Patrik Lambert, Lluís Màrquez, Elena Montiel-Ponsoda
2016 The Journal of Artificial Intelligence Research  
The selected papers cover a broad range of cross-lingual technologies including machine translation, domain and language adaptation for sentiment analysis, cross-language lexical resources, dependency  ...  parsing, information retrieval and knowledge representation.  ...  Acknowledgements The authors want to thank Dan Roth, Mark Sammons and an anonymous reviewer for their useful comments and suggestions on previous versions of this document.  ... 
doi:10.1613/jair.5022 fatcat:h63kjmerufgkxh3qstvegklcyy

Assessing Query Translation Quality Using Back Translation in Hindi-English CLIR

Ganesh Chandra, Sanjay K. Dwivedi
2017 International Journal of Intelligent Systems and Applications  
Cross-Language Information Retrieval (CLIR) is a most demanding research area of Information Retrieval (IR) which deals with retrieval of documents different from query language.  ...  Our analysis shows that back translation can be effective in improving the accuracy of query translation of the three translators used for analysis (i.e. Google, Microsoft and Babylon).  ...  Such type of information retrieval is known as Cross -Lingual Information Retrieval (CLIR) [3, 43, 44] .  ... 
doi:10.5815/ijisa.2017.03.07 fatcat:cdc4h2hy2fbeving5xqdetzp3e

The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval

Constantine Lignos, Daniel Cohen, Yen-Chieh Lien, Pratik Mehta, W. Bruce Croft, Scott Miller
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
When performing cross-language information retrieval (CLIR) for lower-resourced languages, a common approach is to retrieve over the output of machine translation (MT).  ...  In this paper, we examine the relationship between the performance of MT systems and both neural and term frequency-based IR models to identify how CLIR performance can be best predicted from MT quality  ...  Acknowledgements This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via contract  ... 
doi:10.18653/v1/d19-1353 dblp:conf/emnlp/LignosCLMCM19 fatcat:o2mddiiebzfixarva7inbulvny

Adaptive Language Processing Based on Deep Learning in Cloud Computing Platform

Wenbin Xu, Chengbo Yin
2020 Complexity  
Experiments show that both methods have good effects and can effectively improve the translation quality of statistical machines.  ...  Finally, the adaptive method of massive corpus filtering and statistical machine translation based on cloud platform is verified.  ...  source language input by means of information retrieval is very helpful for determining topic information.  ... 
doi:10.1155/2020/5828130 fatcat:ygls6pzwc5emrmupt6ml2tppau

The Cross-Lingual Arabic Information REtrieval (CLAIRE) System [article]

Zhizhong Chen, Carsten Eickhoff
2021 arXiv   pre-print
Despite advances in neural machine translation, cross-lingual retrieval tasks in which queries and documents live in different natural language spaces remain challenging.  ...  In this paper, we build our end-to-end Cross-Lingual Arabic Information REtrieval (CLAIRE) system based on the cross-lingual word embedding where searchers are assumed to have a passable passive understanding  ...  For translation-based approach, Douglas Oard et al. explore methods of translating documents into the query language [19] . And Jianfeng Gao et al. choose to translate queries for eciency [10] .  ... 
arXiv:2107.13751v1 fatcat:nit7lsgg4jdkvmcrz2f6tuk3lu

Cross-Language Pseudo-Relevance Feedback Techniques for Informal Text [chapter]

Chia-Jung Lee, W. Bruce Croft
2014 Lecture Notes in Computer Science  
Previous work has shown that pseudo relevance feedback (PRF) can be effective for cross-lingual information retrieval (CLIR).  ...  To address the problem of the two major sources of "noisy" text, namely translation and the informal nature of the documents, we propose to select between inter-and intra-language PRF, based on the properties  ...  Acknowledgments This work was supported in part by the Center for Intelligent Information Retrieval and in part by IBM subcontract #4913003298 under DARPA prime contract #HR001-12-C-0015.  ... 
doi:10.1007/978-3-319-06028-6_22 fatcat:y3vksyu3pzf2paujai7qcka5ni

The Use of Ontology in Retrieval: A Study on Textual, Multilingual and Multimedia Retrieval

Muhammad Nabeel Asim, Muhammad Wasim, Muhammad Usman Ghani Khan, Nasir Mahmood, Waqar Mahmood
2019 IEEE Access  
This paper reviews modern ontology-based information retrieval methods for textual, multimedia, and cross-lingual data types.  ...  Ontological information retrieval systems retrieve data based on the similarity of semantics between the user query and the indexed data.  ...  Translating all terms perfectly is one of the biggest challenge for cross-language information retrieval system.  ... 
doi:10.1109/access.2019.2897849 fatcat:ei2zxyxdjndbvgzzue2indwqy4

Statistical Machine Translation and Cross-Language IR: QMUL at CLEF 2006

Christof Monz
2006 Conference and Labs of the Evaluation Forum  
In this year's CLEF submissions we focus on using a state-of-the-art statistical machine translation approach for ad-hoc cross-language retrieval.  ...  Our results show that a statistical phrase-based approach is a competitive alternative to commercial, rule-based machine translation approaches in the context of cross-language IR.  ...  Acknowledgments This work has been supported, in part, by the Nuffield Foundation, Grant No. NAL/32720.  ... 
dblp:conf/clef/Monz06 fatcat:rj2dplzhabbunfz5hticyv6ytq

Domain-Specific Query Translation for Multilingual Information Access using Machine Translation Augmented With Dictionaries Mined from Wikipedia

Gareth J. F. Jones, Fabio Fantino, Eamonn Newman, Ying Zhang
2008 International Joint Conference on Natural Language Processing  
Accurate high-coverage translation is a vital component of reliable cross language information access (CLIA) systems.  ...  We demonstrate that effective query translation for CLIA can be achieved in the domain of cultural heritage (CH).  ...  Acknowledgement Work partially supported by European Community under the Information Society Technologies (IST) programme of the 6th FP for RTD -project Mul-tiMATCH contract IST−033104.  ... 
dblp:conf/ijcnlp/JonesFNZ08 fatcat:bnxjrwihrbaelij5rfkjnnhfcm

Ad hoc, Cross-language and Spoken Document Information Retrieval at IBM

Martin Franz, J. Scott McCarley, Todd Ward
1999 Text Retrieval Conference  
Figure 1 : 1 Figure 1: Combining the results based on ASR and translated data 4 Cross-language Track 4.1 Introduction Figure 2 : 2 Figure 2: Scatterplot of average precision on English queries vs.  ...  Then retrieval of automatic transcriptions of broadcast news is considered to be a problem in cross-language information retrieval, since the queries being free of speech recognition errors more closely  ... 
dblp:conf/trec/FranzMW99 fatcat:mnvrzlednzaozpyl6xpufy5ici
« Previous Showing results 1 — 15 out of 30,645 results