Filters








107 Hits in 3.6 sec

Evaluating lexical resources using SENSEVAL

NICOLETTA CALZOLARI, CLAUDIA SORIA, FRANCESCA BERTAGNA, FRANCESCO BARSOTTI
2002 Natural Language Engineering  
description of the Italian lexical sample task for the Senseval-2 experiment.  ...  The aim of our paper is twofold: to introduce some general reflections on the task of lexical semantic annotation and the adequacy of existing lexical-semantic reference resources, while giving an overall  ...  in Italy, aiming at developing large linguistic resources and software tools for the Italian written and spoken language processing.  ... 
doi:10.1017/s1351324902003017 fatcat:6bajslvwy5gtjglm434bmsnhqa

Computational semantic analysis of language: SemEval-2007 and beyond

Eneko Agirre, Lluís Màrquez, Richard Wicentowski
2009 Language Resources and Evaluation  
Acknowledgements We are especially grateful to the numerous reviewers who offered their time and expertise to select the papers presented here.  ...  Also, we thank the authors of submitted papers for their interest and hard work.  ...  Table 1) , and over 100 teams participated with over 123 unique systems. 5 Some tasks were updated versions of the WSD tasks found in Senseval-3, including lexical-sample word sense disambiguation tasks  ... 
doi:10.1007/s10579-009-9091-2 fatcat:kcfwku252zg6pcrznoikzox6wq

SENSEVAL-2: Overview

Philip Edmonds, Scott Cotton
2001 International Workshop on Semantic Evaluation  
This paper gives an overview of SENSEV AL-2, discussing the evaluation exercise, the tasks, the scoring system, and the results. It ends with some recommendations for future evaluation exercises.  ...  SENSEV AL-2: The Second International Workshop on Evaluating Word Sense Disambiguation Systems was held on July 5-6, 2001.  ...  For the lexical sample tasks, it was suggested that for each sample word, at least 75+15n corpus instances be chosen, where n is the number of senses of the word.  ... 
dblp:conf/semeval/EdmondsC01 fatcat:73gle5epkfabxprptc55dcucpm

Introduction to the special issue on evaluating word sense disambiguation systems

PHILIP EDMONDS, ADAM KILGARRIFF
2002 Natural Language Engineering  
Automatic systems don't perform nearly as well as humans on the task, and from the results of the Senseval exercises, recent improvements in system performance appear negligible or even negative.  ...  Indeed, the success of any project in WSD is tied to the evaluation methodology used, and especially to the formalization of the task that the systems perform.  ...  The reviewers were: Eneko Agirre ( We are very grateful to all those who responded to our query to the corpora mailing list in August 2002 regarding the existence and availability of senseannotated resources  ... 
doi:10.1017/s1351324902002966 fatcat:4vx2mnifobbbvjloud4lbua2tq

Kernel Methods for Minimally Supervised WSD

Claudio Giuliano, Alfio Massimiliano Gliozzo, Carlo Strapparava
2009 Computational Linguistics  
The results show that the proposed approach achieves state-of-the-art performance on a wide range of lexical sample tasks and on the English all-words task of Senseval-3, although it uses a considerably  ...  Lexical-Sample Tasks In this section, we report the evaluation of our method on the Catalan, English, Italian, and Spanish lexical-sample tasks of Senseval-3 (Mihalcea and Edmonds 2004) .  ...  3 The 3 performance (F1) of the basic and composite kernels on the Catalan, English, Italian, and Spanish lexical-sample tasks of Semeval-3.  ... 
doi:10.1162/coli.2009.35.4.35407 fatcat:vuw7dqduzvd5tfha7dirtwrbqa

Senseval-3: The Italian all-words task

Marisa Ulivieri, Elisabetta Guazzini, Francesca Bertagna, Nicoletta Calzolari
2004 International Workshop on Semantic Evaluation  
This paper describes the Italian all-words sense disambiguation task for Senseval-3. The annotation procedure and criteria together with the encoding of multiwords are presented.  ...  Introduction This paper describes the Italian all-words sense disambiguation task for Senseval-3: about 5000 words were manually disambiguated according to the ItalWordNet (IWN) word senses.  ...  Multiwords annotation The main difference between Senseval-3 and Senseval-2 is that in the all-words annotation task annotators are faced with complex lexical items coined, generally, with many technical  ... 
dblp:conf/semeval/UlivieriGBC04 fatcat:fjluftzln5aelcgjkocc5k7zse

Persian-WSD-Corpus: A Sense Annotated Corpus for Persian All-words Word Sense Disambiguation [article]

Hossein Rouhizadeh, Mehrnoush Shamsfard, Vahideh Tajalli, Masoud Rouhziadeh
2021 arXiv   pre-print
To this end, three annotators used SAMP (a tool for sense annotation based on FarsNet lexical graph) to perform the annotation task.  ...  The corpus is publicly available at https://github.com/hrouhizadeh/SBU-WSD-Corpus.  ...  The main focus of Senseval-1 through Senseval-3 was on both All-words and Lexical Sample WSD tasks.  ... 
arXiv:2107.01540v1 fatcat:uj3we32vmvebdnctws7yst7vsa

A Survey of WordNet Annotated Corpora

Tommaso Petrolito, Francis Bond
2014 Global WordNet Conference  
We finally discuss possibilities in increasing the interoperability of the corpora, especially across languages. 42 You can find SemCor, Senseval 2 and 3 here, www.cse. unt.edu/~rada/downloads.html#semcor  ...  This paper surveys the current state of wordnet sense annotated corpora. We look at corpora in any language, and describe them in terms of accessibility and usefulness.  ...  We would like to thank Anja Weisscher and Piek Vossen for their help in adding the information to the Global Wordnet Association page.  ... 
dblp:conf/wordnet/PetrolitoB14 fatcat:fnqjbaarrvbgtjpbxhkl3tdfde

Domain kernels for word sense disambiguation

Alfio Gliozzo, Claudio Giuliano, Carlo Strapparava
2005 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05  
We evaluated our methodology on several lexical sample tasks in different languages, outperforming significantly the state-of-the-art for each of them, while reducing the amount of labeled training data  ...  We defined a kernel function, namely the Domain Kernel, that allowed us to plug "external knowledge" into the supervised learning process.  ...  Acknowledgments Alfio Gliozzo and Carlo Strapparava were partially supported by the EU project Meaning (IST-2001-34460). Claudio Giuliano was supported by the EU project Dot.Kom (IST-2001-34038).  ... 
doi:10.3115/1219840.1219890 dblp:conf/acl/GliozzoGS05 fatcat:msiiz3doijelfiw4rtxr5fpamy

Making fine-grained and coarse-grained sense distinctions, both manually and automatically

MARTHA PALMER, HOA TRANG DANG, CHRISTIANE FELLBAUM
2005 Natural Language Engineering  
We investigate sources of human annotator disagreements stemming from the tagging for the English Verb Lexical Sample Task in the Senseval-2 exercise in automatic Word Sense Disambiguation.  ...  Both sets of errors are at least partially reconciled by a more coarse-grained view of the senses, and we present the groupings we use for quantitative coarse-grained evaluation as well as the process  ...  subcontract to University of Pennsylvania 2003-07911-01 and DARPA grant N66001-00-1-8915 at the University of Pennsylvania, as well as the CIA (contract number 2000*SO53100*000).  ... 
doi:10.1017/s135132490500402x fatcat:acn6h2n5rfhthjspvzeu2yebtu

Word sense disambiguation

Roberto Navigli
2009 ACM Computing Surveys  
The assessment of WSD systems is discussed in the context of the Senseval/Semeval campaigns, aiming at the objective evaluation of systems participating in several different disambiguation tasks.  ...  WSD is considered an AI-complete problem, that is, a task whose solution is at least as hard as the most difficult problems in artificial intelligence.  ...  and the four anonymous reviewers for their useful comments.  ... 
doi:10.1145/1459352.1459355 fatcat:jchhwe4xcjbbnjsqblynshli7i

Distinguishing systems and distinguishing senses: new evaluation methods for Word Sense Disambiguation

PHILIP RESNIK, DAVID YAROWSKY
1999 Natural Language Engineering  
Subsequent discussion of those proposals resulted in senseval, the rst evaluation exercise for word sense disambiguation (Kilgarri and Palmer forthcoming).  ...  In addition, the probability that a given sense pair will tend to lexicalize di erently across languages is shown to correlate with semantic salience and sense granularity; sense hierarchies automatically  ...  For English, at least, performance of state-ofthe-art systems on other lexical tasks such as part-of-speech (POS) tagging and morphological analysis is respectable, if not perfect, and the dominant approaches  ... 
doi:10.1017/s1351324999002211 fatcat:6eklgqdofjcevd6khafmjcdyni

Structural semantic interconnections: a knowledge-based approach to word sense disambiguation

R. Navigli, P. Velardi
2005 IEEE Transactions on Pattern Analysis and Machine Intelligence  
On the other hand, the increasing availability of large-scale, rich lexical knowledge resources seems to provide new challenges to knowledge-based approaches.  ...  Sense specifications are created from several available lexical resources that we integrated in part manually, in part with the help of automatic procedures.  ...  ACKNOWLEDGMENTS This work has been partly funded by the Italian Legenda MIUR project on cultural tourism and by the EC INTEROP Network of Excellence on enterprise interoperability.  ... 
doi:10.1109/tpami.2005.149 pmid:16013755 fatcat:3za2wf7itvc37jpaxc7gwdneom

A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation

Ali Saeed, Rao Muhammad Adeel Nawab, Mark Stevenson, Paul Rayson
2019 ACM Transactions on Asian and Low-Resource Language Information Processing  
To ill this gap, this study proposes a novel benchmark corpus for the Urdu All-Words WSD task.  ...  The corpus is freely available to the research community to encourage further WSD research in Urdu.  ...  Nivigli [45] noted that supervised approaches are useful for the Lexical Sample WSD task.  ... 
doi:10.1145/3314940 fatcat:awjrtihv6vew7eusjakt4snxjy

SemEval-2007 Task 07: Coarse-Grained English All-Words Task

Roberto Navigli, Kenneth C. Litkowski, Orin Hargraves
2007 International Workshop on Semantic Evaluation  
This paper presents the coarse-grained English all-words task at SemEval-2007.  ...  We describe our experience in producing a coarse version of the WordNet sense inventory and preparing the sense-tagged corpus for the task.  ...  Acknowledgments This work was partially funded by the Interop NoE (508011), 6 th European Union FP. We would like to thank Martha Palmer for providing us the first three texts of the test corpus.  ... 
dblp:conf/semeval/NavigliLH07 fatcat:hup4s4an2beepgo2vhrvvwut3i
« Previous Showing results 1 — 15 out of 107 results