81,305 Hits in 8.8 sec

Evaluating Interactive Cross-Language Information Retrieval: Document Selection [chapter]

Douglas W. Oard
2001 Lecture Notes in Computer Science  
The problem of nding documents that are written in a language that the searcher cannot read is perhaps the most challenging application of Cross-Language Information Retrieval (CLIR) technology.  ...  This paper explores the question of how i nteractive approaches to CLIR might b e e v aluated, suggesting an initial focus on evaluation of interactive document selection.  ...  Acknowledgments The author is grateful to the participants in the June 2000 workshop on interactive cross-language retrieval, and especially to Bill Ogden, Gina Levow and Jian-qiang Wang, for stimulating  ... 
doi:10.1007/3-540-44645-1_6 fatcat:t3dkqaaqfzavlhywf3nchz2y24

Support for interactive document selection in cross-language information retrieval

Douglas W. Oard, Philip Resnik
1999 Information Processing & Management  
This article describes the interactions among these components and presents a practical way of evaluating the adequacy of the selection interface.  ...  As digital libraries grow to global scale, the provision of interactive access to content in many languages will become increasingly important.  ...  selection in cross-language information retrieval.  ... 
doi:10.1016/s0306-4573(98)00066-1 fatcat:3rj3nzcs6jcolmoa4ch4iguljm

First Experiments with Relevant Documents Selection for Blind Relevance Feedback in Spoken Document Retrieval [chapter]

Lucie Skorkovská
2014 Lecture Notes in Computer Science  
This paper presents our first experiments aimed at the automatic selection of the relevant documents for the blind relevance feedback method in speech information retrieval.  ...  Usually the relevant documents are selected only by simply determining the first N documents to be relevant.  ...  Information Retrieval Collection Our experiments were performed on the spoken document retrieval collection that was used in the Czech task of the Cross-Language Speech Retrieval track organized within  ... 
doi:10.1007/978-3-319-11581-8_29 fatcat:qdfgc6tvzrcprj4y642cjw3tfq

The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval [article]

Minghan Li, Diana Nicoleta Popa, Johan Chagnon, Yagmur Gizem Cinar, Eric Gaussier
2021 arXiv   pre-print
On a wide range of natural language processing and information retrieval tasks, transformer-based models, particularly pre-trained language models like BERT, have demonstrated tremendous effectiveness.  ...  We follow here a slightly different approach in which one first selects key blocks of a long document by local query-block pre-ranking, and then few blocks are aggregated to form a short document that  ...  information retrieval, where each document could contain thousands of tokens.  ... 
arXiv:2111.09852v2 fatcat:iu6tm4xchzcufg43rx5lykawia

Document selection methodologies for efficient and effective learning-to-rank

Javed A. Aslam, Evangelos Kanoulas, Virgil Pavlu, Stefan Savev, Emine Yilmaz
2009 Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval - SIGIR '09  
We compare them with the document selection methodology used to create the LETOR datasets.  ...  Certain methodologies, e.g. sampling and active-learning, have been shown to lead to efficient and effective evaluation.  ...  INTRODUCTION Ranking is a central problem in information retrieval.  ... 
doi:10.1145/1571941.1572022 dblp:conf/sigir/AslamKPSY09 fatcat:7eunxfursfdjfh4drowqjygcbu

iCLEF 2003 at Maryland: Translation Selection and Document Selection [chapter]

Bonnie Dorr, Daqing He, Jun Luo, Douglas W. Oard, Richard Schwartz, Jianqiang Wang, David Zajic
2004 Lecture Notes in Computer Science  
Maryland performed two sets of experiments for the 2003 Cross-Language Evaluation Forum's interactive track, one focused on interactive selection of appropriate translations for query terms, the second  ...  focused on interactive selection of relevant documents.  ...  Introduction The goal of Cross-Language Information Retrieval (CLIR) is to help searchers find relevant documents even when their query terms are chosen from a language different from the language in which  ... 
doi:10.1007/978-3-540-30222-3_42 fatcat:dp4foak2j5gzhn43kvem5bigvq

Feature selection on hierarchy of web documents

Dunja Mladenić, Marko Grobelnik
2003 Decision Support Systems  
The best performance was achieved by the feature selection based on a feature scoring measure known from information retrieval called Odds ratio and using relatively small number of features.  ...  Experimental evaluation on real-world data shows that the proposed approach g i v es good results.  ...  The actual Web documents these items point t o a r e used as the testing documents. Evaluation Precision and recall are model quality estimates commonly used in information retrieval.  ... 
doi:10.1016/s0167-9236(02)00097-0 fatcat:qhverop3vzhfpk4k75wrfitvq4

Retrieval Effectiveness of Cross Language Information Retrieval Search Engines [chapter]

Schubert Foo
2011 Lecture Notes in Computer Science  
This study evaluates the retrieval effectiveness of English-Chinese (EC) cross-language information retrieval (CLIR) on four common search engines along the dimensions of recall and precision.  ...  Three independent bilingual proficient evaluators reviewed a total of 960 returned web pages each to assess document relevance.  ...  (Information Studies) program.  ... 
doi:10.1007/978-3-642-24826-9_37 fatcat:cfheaohlg5hr5fxbajzi6y45hi

Cross-Language Information Retrieval [chapter]

Carol Peters, Martin Braschler, Paul Clough
2011 Multilingual Information Retrieval  
system development in the directions identified n Cross-language multimodal systems n Multilingual question answering n Cross-language interactive systems Multilingual Text Retrieval (MLTR) ETD: 2007  ...  text retrieval system searching on collections in at least five language with functionality for user-assisted query formulation, refinement, document selection and interpretation.  ... 
doi:10.1007/978-3-642-23008-0_3 fatcat:mekyygkxmbc5vjin3kjgmxm3uy

Cross-language Information Retrieval [article]

Petra Galuščáková, Douglas W. Oard, Suraj Nair
2022 arXiv   pre-print
When the documents to be searched are in a language not known by the searcher, neither assumption is true. In such cases, Cross-Language Information Retrieval (CLIR) is needed.  ...  Two key assumptions shape the usual view of ranked retrieval: (1) that the searcher can choose words for their query that might appear in the documents that they wish to see, and (2) that ranking retrieved  ...  As its name suggests, a range of CLIR-related tasks were organized at CLEF, including ad-hoc CLIR and domain specific CLIR, interactive CLIR, Cross-Language Spoken Document Retrieval and Cross-Language  ... 
arXiv:2111.05988v2 fatcat:4f3qbtcswvdavhzhufehdlbyry

Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents [article]

Ming Tu, Kevin Huang, Guangtao Wang, Jing Huang, Xiaodong He, Bowen Zhou
2020 arXiv   pre-print
Our system first filters out answer-unrelated documents and thus reduce the amount of distraction information.  ...  The selected answer-related documents are then input to a model to jointly predict the answer and supporting sentences.  ...  We would like to thank Peng Qi of Stanford University for running evaluation on our submitted models. This work is partially supported by Beijing Academy of Artificial Intelligence (BAAI).  ... 
arXiv:1911.00484v4 fatcat:g4tcfsvfcjg53ireba5unr652u

Arabic Information Retrieval

Kareem Darwish
2014 Foundations and Trends in Information Retrieval  
Evaluation of Multilingual and Multi-modal Information Retrieval, In 2007 Cross-Language Evaluation Forum (CLEF). [71] Jiafeng Guo, Gu Xu, Xueqi Cheng, and Hang Li. 2009.  ...  Evaluating Systems for Multilingual and Multi- modal Information Access, in the 2009 Cross-Language Evaluation Fo- rum (CLEF), pp. 939-946.  ... 
doi:10.1561/1500000031 fatcat:2nxjdu43erhdvbs35ykavrk76a

Adversarial Retriever-Ranker for dense text retrieval [article]

Hang Zhang, Yeyun Gong, Yelong Shen, Jiancheng Lv, Nan Duan, Weizhu Chen
2022 arXiv   pre-print
Through this adversarial game, the retriever gradually produces harder negative documents to train a better ranker, whereas the cross-encoder ranker provides progressive feedback to improve retriever.  ...  We evaluate AR2 on three benchmarks.  ...  Then we train a warm-up cross-encoder model D0 initialized with the ERNIE-2.0-Large. D0 learns to rank the Top-k documents selected by G0 with contrastive learning.  ... 
arXiv:2110.03611v4 fatcat:viizovgh3jbu5mnlnclsjmfyam

Cross-Lingual Training with Dense Retrieval for Document Retrieval [article]

Peng Shi, Rui Zhang, He Bai, Jimmy Lin
2021 arXiv   pre-print
However, its effectiveness in document retrieval for non-English languages remains unexplored due to the limitation in training resources.  ...  In this work, we explore different transfer techniques for document ranking from English annotations to multiple non-English languages.  ...  Note that this setting is different from cross-lingual information retrieval (CLIR), where queries and documents are in different languages (Shi and Lin, 2019; Yu and Allan, 2020; Jiang et al., 2020;  ... 
arXiv:2109.01628v1 fatcat:ogrosnckcjcjlco3hdb4cqsrwe

Information Retrieval - From Information Access to Contextual Retrieval

Norbert Fuhr
2020 Zenodo  
Information Retrieval (IR) deals with uncertainty and vagueness in in-formation systems.  ...  On the other hands, information needs to be answered by IR systems are often vague and cannot be specified precisely, thus leading to iterative query formu-lation. [...]  ...  Text Retrieval Conference Homepage. [Zugriff September 2004]. 3 Cross Language Evaluation Forum (CKEF) (2004).  ... 
doi:10.5281/zenodo.4136995 fatcat:ufop5acffbaczf2po7c5hntsti
« Previous Showing results 1 — 15 out of 81,305 results