A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
COLE Experiments at CLEF 2003 in the Spanish Monolingual Track
[chapter]
2004
Lecture Notes in Computer Science
Preserved Fulltext
In this our second participation in the CLEF Spanish monolingual track, we have continued applying Natural Language Processing techniques for single word and multi-word term conflation. ...
Our previous experiments in CLEF 2002 showed that lemmatization performs better than stemming, even when using stemmers which also deals with derivational morphology. ...
The set of topics has also been enlarged; this year it consists of 60 queries (141 to 200) instead of 50 as previous years.Our group submitted four runs to the CLEF 2003 Spanish monolingual track:
Table ...
doi:10.1007/978-3-540-30222-3_33
fatcat:4nkb2qf4kredriljtbbykhfr64
COLE Experiments in the CLEF 2002 Spanish Monolingual Track
[chapter]
2003
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We tested several approaches at different levels of text processing in our experiments: first, we lemmatized the text to avoid inflectional variation; second, we expanded the queries through synonyms according ...
In this our first participation in CLEF, we applied Natural Language Processing techniques for single word and multiword term conflation. ...
The effectiveness of our solutions has been tested during this our first participation in the CLEF Spanish monolingual track. This article is structured as follows. ...
doi:10.1007/978-3-540-45237-9_22
fatcat:rvesai4nwzfztbg2ulp6wawgga
CoLesIR at CLEF 2006: Rapid Prototyping of an N-gram-Based CLIR System
2006
Conference and Labs of the Evaluation Forum
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this our first joint participation as the CoLesIR group, our team has participated in the Portuguese monolingual ad-hoc task and in all robust ad-hoc tasks -all monolingual tasks, the English-to-German ...
Section 4 shows the results obtained in our participation in both the Portuguese monolingual and robust tasks of the CLEF 2006 ad-hoc track. ...
The robust task is essentially an ad-hoc task which makes use of the topics and collections used from CLEF 2001 to CLEF 2003. ...
dblp:conf/clef/VilaresOT06a
fatcat:jjfqa5k52bb45a66qhpbyqeh7e
Cross-language Information Retrieval
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The multiple language question answering track
at CLEF 2003. In CLEF, volume 3237, 08 2003.
[121] B. Magnini, A. Vallin, C. Ayache, G. Erbach, A. Peñas, M. de Rijke,
P. Rocha, K. ...
The CLEF 2003 cross-language spoken docu-
ment retrieval track. In CLEF, volume 3237, page 646, 08 2003.
[48] M. Federico, N. Bertoldi, G.-A. Levow, and G. J. F. Jones. ...
arXiv:2111.05988v2
fatcat:4f3qbtcswvdavhzhufehdlbyry
Introduction to the Special Issue on Cross-Language Algorithms and Applications
2016
The Journal of Artificial Intelligence Research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
News Across Languages -Cross-Lingual Document Similarity and Event Tracking by Rupnik, Muhic, Leban, Skraba, Fortuna and Grobelnik addresses the problem of event tracking in a large multilingual stream ...
Among the three sources, leveraging video titles improves retrieval performance in their experiments. ...
doi:10.1613/jair.5022
fatcat:h63kjmerufgkxh3qstvegklcyy
One Model to Rule them all: Multitask and Multilingual Modelling for Lexical Analysis
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The traditional approach in NLP is to consider a single task for a single language at a time. ...
Mainly, it seems to be the case that this approach is suitable when training on a monolingual source pair (such as English-English), and evaluating the model on a monolingual target pair (such as Spanish-Spanish ...
We observe that the monolingual language pairings (English-English, Spanish-Spanish, Arabic-Arabic) appear to be beneficial for one another, also in this setting. ...
arXiv:1711.01100v1
fatcat:njotlhapbjggxkfndwa3wkwg4q
A Review of Question Answering Systems
2019
Journal of Web Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
QA4MRE@CLEF 2013. is a Ph.D. student at the Federal University of Technology, Akure since March 2019. ...
Results from the experiments carried out by Chu-Carol (2003) illustrates substantial performance enhancement by merging statistical and linguistic methods to QA. ...
doi:10.13052/jwe1540-9589.1785
fatcat:g4bbctufvjd6fkijclxd5rnth4
Deep Learning for Text Style Transfer: A Survey
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our curated paper list is at https://github.com/zhijing-jin/Text_Style_Transfer_Survey ...
Reformulating unsupervised
obfuscation - (best of the labs track at style transfer as paraphrase generation.
CLEF-2017). ...
wordnet and language models—notebook
Luo, Fuli, Peng Li, Jie Zhou, Pengcheng Yang, for pan at clef 2016. In CLEF 2016
Baobao Chang, Zhifang Sui, and Xu Sun. ...
arXiv:2011.00416v5
fatcat:wfw3jfh2mjfupbzrmnztsqy4ny
Deep Learning for Text Style Transfer: A Survey
2021
Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Reformulating unsupervised
obfuscation - (best of the labs track at style transfer as paraphrase generation.
CLEF-2017). ...
wordnet and language models—notebook
Luo, Fuli, Peng Li, Jie Zhou, Pengcheng Yang, for pan at clef 2016. In CLEF 2016
Baobao Chang, Zhifang Sui, and Xu Sun. ...
doi:10.1162/coli_a_00426
fatcat:v7vmb62ckfcu5k5mpu2pydnrxy
Discourse in Statistical Machine Translation
2012
Discours
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
By creating a framework for experimenting with discourse-level features in SMT, this work contributes to a long-term perspective that strives for more thorough modelling of complex linguistic phenomena ...
The experiments were carried out by Sara Stymne.
The stop word list was retrieved from http://members.unine.ch/jacques.savoy/clef/ frenchST.txt(12 October 2011). ...
., 2003) . ...
doi:10.4000/discours.8726
fatcat:gxkpd2ubvzbjna7f7hw62oicg4
***INVITED TALK***: Handling and Mining Linguistic Variation in UGC Distributed Representations of Words and Documents for Discriminating Similar Languages
2015
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
VarDial workshop at COLING2014. ...
Examples of pairs of related languages include Swedish-Norwegian, Bulgarian-Macedonian, Serbian-Bosnian, Spanish-Catalan, Russian-Ukrainian, Irish-Gaelic Scottish, Malay-Indonesian, Turkish-Azerbaijani ...
The work of the third author was partially funded by Autoritas Consulting SA and by Spanish Ministry of Economics under grant ECOPOR-TUNITY IPT-2012-1220-430000. ...
fatcat:am5wftv4o5gmtbfzcw3iubpp2i
Introduction to the Special Issue on Cross-Language Algorithms and Applications
2016
Journal of Artificial Intelligence Research
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
News Across Languages -Cross-Lingual Document Similarity and Event Tracking by Rupnik, Muhic, Leban, Skraba, Fortuna and Grobelnik addresses the problem of event tracking in a large multilingual stream ...
Among the three sources, leveraging video titles improves retrieval performance in their experiments. ...
fatcat:isfvgjvju5eqnl5txuysb2i5ou
Pluricentric languages : automatic identification and linguistic variation
[article]
2016
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Finnish and Spanish), or due to the contrast between languages with unique character sets such as Greek or Hebrew. ...
The main objective is to investigate the extent to which it is possible to identify language varieties automatically in both monolingual and in real-world (multilingual) settings and to establish what ...
19 at EMNLP 2014, the VarDial 20 workshop at COLING 2014, and the most recent event, LT4VarDial 21 held at RANLP 2015. ...
doi:10.22028/d291-23660
fatcat:um5riv7ffvg4te7eqprfnbjyem
Ivelina Nikolova and Natalia Konstantinova Organisers of the Student Workshop
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
We both experiment with rule-based methods and machine learning approaches. ...
Acknowledgments This work was supported by the Project "TÁMOP-4.2.1/B-09/1/KONV-2010-0005 -Creating the Center of Excellence at the University of Szeged", supported by the European Union and co-financed ...
The corpus The corpus is made up of 100 questions extracted from monolingual Spanish sets of CLEF 7 2004, 2006 and 2007. All the examples in the corpus are wh-questions. ...
fatcat:uxotu5b5mbh6jmf5wo4een7pda
Methods for morphology learning in low(er)-resource scenarios
[article]
2020
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 1029-1037, Beijing, China, August. Coling 2010 Organizing Committee. ...
For experiments with j > 1 examples per type, we first find all UM types with at least j sentence contexts in Wikipedia and then choose the N distinct types and their j contexts uniformly at random. ...
doi:10.7488/era/416
fatcat:glj6gvapezduzix5mvzdpl6ama
« Previous
Showing results 1 — 15 out of 20 results