218 Hits in 7.7 sec

Temporal Information Access [chapter]

Masaharu Yoshioka, Hideo Joho
2020 Evaluating Information Retrieval and Access Tasks  
This chapter introduces the research background and details of temporal information access tasks in the NTCIR.  ...  The GeoTime task was the first attempt to evaluate temporal information retrieval as an extension of an information-retrievalfor-question-answering task.  ...  The authors also thank all participants in the tasks for their interest and contributions to the technological advance in temporal information access.  ... 
doi:10.1007/978-981-15-5554-1_9 fatcat:kpgqz3s7jfgy3ajkmafeqnanoi

Evaluation Framework Design of Spoken Term Detection Study at the NTCIR-9 IR for Spoken Documents Task

Hiromitsu Nishizaki, Tomoyosi Akiba, Kiyoaki Aikawa, Tatsuya Kawahara, Tomoko Matsui
2012 Journal of Natural Language Processing  
This paper describes a design of spoken term detection (STD) studies and their evaluating framework at the STD sub-task of the NTCIR-9 IR for Spoken Documents (SpokenDoc) task.  ...  of the participants' techniques, and the evaluation results of the task participants.  ...  A part of the paper's content has been presented at the 9-th NTCIR Workshop meeting .  ... 
doi:10.5715/jnlp.19.329 fatcat:p3zdvdtmajhltjgx2d6z7fio4a

Selecting Effective Terms for Query Formulation [chapter]

Chia-Jung Lee, Yi-Chun Lin, Ruey-Cheng Chen, Pu-Jen Cheng
2009 Lecture Notes in Computer Science  
Experiments on NTCIR-4 and NTCIR-5 ad-hoc IR tasks demonstrate that the algorithms can significantly improve the retrieval performance by 9.2% averagely, compared to the performance of the original queries  ...  In this paper, we propose an approach to query term selection by measuring the effectiveness of a query term in IR systems based on its linguistic and statistical properties in document collections.  ...  However, their focus is to evaluate performance of a whole query whereas we consider units at the level of terms.  ... 
doi:10.1007/978-3-642-04769-5_15 fatcat:wbr7azpoabhztma3uwo5uipbvu

Query Generation Techniques for Patent Prior-Art Search in Multiple Languages [chapter]

Dong Zhou, Jianxun Liu, Sanrong Zhang
2013 Communications in Computer and Information Science  
A detail comparison of the different methods in terms of performance and efficiency has been performed in addition to the use of full-length documents as queries in the patent search.  ...  The results show that some methods, work well in information retrieval in general, fail to achieve the same effectiveness in the patent search.  ...  Statistically-significant differences in performance were determined using a paired t-test at a confidence level of 95%.  ... 
doi:10.1007/978-3-642-41644-6_29 fatcat:mkh6mngo6vbqxj764bn6ahq4im

An evaluation of the Web retrieval task at the third NTCIR workshop

Koji Eguchi, Keizo Oyama, Emi Ishida, Noriko Kando, Kazuko Kuriyama
2004 SIGIR Forum  
This paper gives an overview of the Web Retrieval Task that was conducted from 2001 to 2002 at the Third NTCIR Workshop.  ...  In the Web Retrieval Task, we attempted to assess the retrieval effectiveness of Web search engine systems using a common data set, and built a re-usable test collection suitable for evaluating Web search  ...  We greatly appreciate the efforts of all the participants of the Web Retrieval Task at the Third NTCIR Workshop.  ... 
doi:10.1145/986278.986285 fatcat:z6rg3kvttngyze7g2slffmuepa

Prior Art Search Using International Patent Classification Codes and All-Claims-Queries [chapter]

Benjamin Herbert, György Szarvas, Iryna Gurevych
2010 Lecture Notes in Computer Science  
We also formulated a language-independent query using the IPC codes of a document to improve the coverage and to obtain a more accurate ranking of candidates.  ...  art candidates and tried to incorporate this information to our system's ranking process.  ...  Invalidity Search was addressed at NTCIR-4 [4] using a document collection of Japanese patents published between 1993 and 2002.  ... 
doi:10.1007/978-3-642-15754-7_54 fatcat:wonl6h5js5bdrokluusmoxaj2m

Query Enhancement for Patent Prior-Art-Search Based on Keyterm Dependency Relations and Semantic Tags [chapter]

Khanh-Ly Nguyen, Sung-Hyon Myaeng
2012 Lecture Notes in Computer Science  
Current patent search systems are mostly keyword-based, and due to the unique characteristics of patents and their usage, such as embedded structure and the length of patent documents, there are rooms  ...  The key idea of this paper is to make use of patent structure, linguistic clues and use word relations to identify important terms.  ...  The increasing amount and the growing need to access patent information require new methodologies and techniques to shorten search time and increase the quality of the search output to eventually increase  ... 
doi:10.1007/978-3-642-31274-8_3 fatcat:5j6c4cse6zg5xdrriaw57mlxq4

A Multimodal Retrieval and Ranking Method for Scientific Documents Based on HFS and XLNet

Meichao Yan, Yu Wen, Qingxuan Shi, Xuedong Tian, Liang Zhao
2022 Scientific Programming  
Finally, the multimodal evaluation is integrated, and the hesitation fuzzy set is constructed at the document level to obtain the final scores of the scientific documents and corresponding ranked output  ...  Aiming at the defects of traditional full-text retrieval models in dealing with mathematical expressions, which are special objects different from ordinary texts, a multimodal retrieval and ranking method  ...  F2019201329), and the Science and Technology Project of Hebei Education Department (No. QN2018214).  ... 
doi:10.1155/2022/5373531 fatcat:nxqd5klvqzc7va4grne3a6kd2m

Patent Retrieval: A Literature Review [article]

Walid Shalaby, Wlodek Zadrozny
2017 arXiv   pre-print
PR is a subfield of Information Retrieval (IR) which is concerned with developing techniques and methods that effectively and efficiently retrieve relevant patent documents in response to a given search  ...  Furthermore, state-of-the-art performance in automatic PR is still around average in terms of recall.  ...  NTCIR-4: two PR tasks were organized in NTCIR-4 [10] : 1) patent map generation, and 2) invalidity search.  ... 
arXiv:1701.00324v1 fatcat:u5w55z4cj5cwbii5s55rjvegvi

Spoken Term Detection Using Phoneme Transition Network from Multiple Speech Recognizers' Outputs

Satoshi Natori, Yuto Furuya, Hiromitsu Nishizaki, Yoshihiro Sekiguchi
2013 Journal of Information Processing  
Since PTNformed index is based on the outputs of multiple speech recognizers, it is robust to recognition errors.  ...  Furthermore, we applied two false detection control parameters, one is based on the majority voting scheme. The other is a measure of the ambiguity of CN, to the calculation of detection score.  ...  Although there is an increasing need to retrieve such spoken information, there are currently no effective retrieval techniques to meet these needs.  ... 
doi:10.2197/ipsjjip.21.176 fatcat:l5g5le2bi5gs7m3epkpsd7yfce

NTCIR-12 Lifelog Data Analytics

Na Li, Cathal Gurrin, Martin Crane, Heather J. Ruskin
2016 Proceedings of the first Workshop on Lifelogging Tools and Applications - LTA '16  
NTCIR-12 Lifelog 1 test collection was initially created, as support for the Information Retrieval (IR) community, to develop new and novel lifelogging retrieval and visualisation systems.  ...  In this paper, our goal is organising and analysing the NTCIR-12 Lifelog dataset by using a time series approach to facilitate automatic discovery of repeat events.  ...  Unlike the DWT, the MODWT has a high level of redundancy. However, it is non-orthogonal and can handle any sample size N , whereas the DWT restricts the sample size to a multiple of 2 j .  ... 
doi:10.1145/2983576.2983583 fatcat:dbxpeme3pngoxadvauk7glv2me

The test collection for navigational retrieval on WWW data-Design and characteristics

Keizo Oyama, Haruko Ishikawa, Koji Eguchi, Akiko Aizawa
2005 Progress in Informatics  
This paper describes the design and characteristics of a test collection for navigational retrieval of WWW data that was built through the WEB Task of the Fourth NTCIR Workshop to evaluate the retrieval  ...  Using the judgment results, several evaluation measures were applied to various retrieval results.  ...  We greatly appreciate the efforts of all the participants of the Navigational Retrieval Task 1 of the WEB Task at the Fourth NTCIR Workshop.  ... 
doi:10.2201/niipi.2005.1.5 fatcat:bv62r52otngh7dzlwwsicrohyu

Efficient Algorithm for Math Formula Semantic Search

Shunsuke OHASHI, Giovanni Yoko KRISTIANTO, Goran TOPIC, Akiko AIZAWA
2016 IEICE transactions on information and systems  
The increasing number as well as the structural complexity of mathematical formulae in scientific articles lead to the necessity for large-scale structureaware formula search techniques.  ...  while also keeps the scalability and runtime efficiency high.  ...  As you can see in Algorithm 4, there are only two types of the operation applied to a hash value, multiplication by constant a and addition.  ... 
doi:10.1587/transinf.2015dap0023 fatcat:56pl6nmhrzdbrcxw3lbej2glh4

Wikipedia-based query phrase expansion in patent class search

Bashar Al-Shboul, Sung-Hyon Myaeng
2013 Information retrieval (Boston)  
Topic drift is an important issue in patent information retrieval as people tend to use different expressions describing similar concepts causing low precision and recall at the same time.  ...  More specifically, our query expansion method was compared against relevance-based language model, a state-of-the-art query expansion method, to show its superiority in terms of MAP on all levels of the  ...  We would like to thank the reviewers for their valuable comments and suggestions that helped improve the quality of this paper.  ... 
doi:10.1007/s10791-013-9233-4 fatcat:ivjoquseu5hctgilqpbo75howm

CRL at Ntcir2 [article]

Masaki Murata, Masao Utiyama, Qing Ma, Hiromi Ozaku, Hitoshi Isahara
2001 arXiv   pre-print
A variety of parameters were tried with the system. It used such characteristics of newspapers as locational information in the CC tasks. The system got good results for both of the tasks.  ...  The system automatically determined the number of top documents and the weight of the original query used in automatic-feedback retrieval. It also determined relevant terms quite robustly.  ...  Summary System A uses such characteristics of newspapers as locational information and obtained good results in the CC Tasks.  ... 
arXiv:cs/0103013v1 fatcat:ta2h5ilik5fulpohbu7jajerca
« Previous Showing results 1 — 15 out of 218 results