39 Hits in 6.2 sec

A Combination of Classifiers for the Pronominal Anaphora Resolution in Basque [chapter]

Ana Zelaia Jauregi, Basilio Sierra, Olatz Arregi Uriarte, Klara Ceberio, Arantza Díaz de Illarraza, Iakes Goenaga
2010 Lecture Notes in Computer Science  
In this paper we present a machine learning approach to resolve the pronominal anaphora in Basque language.  ...  The main contribution of the paper is the use of bagging having as base classifier a non-soft one for the anaphora resolution in Basque.  ...  Acknowledgments This work was supported in part by KNOW2 (TIN2009-14715-C04-01) and Berbatek (IE09-262) projects.  ... 
doi:10.1007/978-3-642-16687-7_36 fatcat:5yiao5logne5dbfej5jruc43zm

A Hybrid Approach to Pronominal Anaphora Resolution in Arabic

Abdullatif Abolohom, Nazlia Omar
2015 Journal of Computer Science  
The hybrid model adopted the strategy based on the combination of a rule-based and machine learning approach.  ...  In this study, a hybrid approach that combines different architectures for resolving pronominal anaphora in Arabic language is presented.  ...  Funding Information The authors have no support or funding to report. Author's Contributions All authors equally contributed in this work.  ... 
doi:10.3844/jcssp.2015.764.771 fatcat:tvr7y2zag5duzg7vilwtptnvtq

Abstract Anaphors in German and English [chapter]

Stefanie Dipper, Christine Rieger, Melanie Seiss, Heike Zinsmeister
2011 Lecture Notes in Computer Science  
anaphors refer to abstract referents such as facts or events. Automatic resolution of this kind of anaphora still poses a problem for language processing systems.  ...  We successively expand this set in a cross-linguistic bootstrapping approach by collecting translation equivalents from English and using them to track down further forms of German anaphors, and, in the  ...  In contrast to the first approach described above, this bootstrapping approach allows for a fast and efficient way of extracting anaphors in both languages.  ... 
doi:10.1007/978-3-642-25917-3_9 fatcat:izmgzu4e6vd3fnfix4ch3rgzhi

Recent advances in Apertium, a free/open-source rule-based machine translation platform for low-resource languages

Tanmai Khanna, Jonathan N. Washington, Francis M. Tyers, Sevilay Bayatlı, Daniel G. Swanson, Tommi A. Pirinen, Irene Tang, Hèctor Alòs i Font
2021 Machine Translation  
that deals with contiguous and discontiguous multi-word expressions, and a module that resolves anaphora to aid translation.  ...  Translation in Apertium happens through a pipeline of modular tools, and the platform continues to be improved as more language pairs are added.  ...  their generous support in covering openaccess publication costs.  ... 
doi:10.1007/s10590-021-09260-6 fatcat:2e54icfjfnbqpobjluwjfkbjaq

Error analysis for anaphora resolution in Russian: new challenging issues for anaphora resolution task in a morphologically rich language

Svetlana Toldova, Ilya Azerkovich, Alina Ladygina, Anna Roitberg, Maria Vasilyeva
2016 Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016)  
of anaphora resolution systems.  ...  This paper presents a quantitative and qualitative error analysis of Russian anaphora resolvers which participated in the RU-EVAL event.  ...  RuCor RuCor consists of two parts, manually annotated for pronominal anaphora and coreference resolution tasks: the learning set and the evaluation set, 185 texts (200 000 tokens) in total.  ... 
doi:10.18653/v1/w16-0711 dblp:conf/naacl/ToldovaALRV16 fatcat:afh6qyll7je77gqr5v2f4kp6u4

EUSKOR: End-to-end coreference resolution system for Basque

Ander Soraluze, Olatz Arregi, Xabier Arregi, Arantza Díaz de Ilarraza, Natalia Grabar
2019 PLoS ONE  
The module has been integrated in a linguistic analysis pipeline obtaining an end-to-end coreference resolution system for the Basque language.  ...  During the experimentation phase, we have demonstrated that language-specific features have a noteworthy effect on coreference resolution, obtaining a gain in CoNLL score of 7.07 with respect to the baseline  ...  Acknowledgments This work has been supported by Ander Soraluze's PhD grant from Euskara Errektoreordetza, the University of the Basque Country (UPV/EHU) and by the PROSAMED project, Spanish Government  ... 
doi:10.1371/journal.pone.0221801 pmid:31513627 pmcid:PMC6742394 fatcat:bwfi3a54bbgzhbu56n5dzys3ay

Neural coreference resolution for Slovene language

Matej Klemen, Slavko Zitnik
2021 Computer Science and Information Systems  
In this work we first present SentiCoref 1.0 - a coreference resolution dataset for Slovene language that is comparable to English-based corpora.  ...  Cross-domain experiments indicate that SentiCoref allows the models to learn more general patterns, which enables them to outperform models, learned on coref149 only.  ...  Acknowledgements The work presented in this paper started as a project in a natural language processing course and was then improved upon with additional experiments.  ... 
doi:10.2298/csis201120060k fatcat:2cwd2hddvffs7po6anmtor34du

Tutorial: Data-driven text simplification

Horacio Saggion, Sanja Štajner
2019 Zenodo  
We aim to break some common misconceptions about what text simplification is and what it is not, and how much it has in common with text summarisation and machine translation.  ...  We will describe and explain all the most influential methods used for automatic simplification of texts so far, with the emphasis on their strengths and weaknesses noticed in a direct comparison of systems  ...  First ap- proach to automatic text simplification in Basque. In Proceedings of the First Workshop on Natural Language Processing for Improving Textual Accessibility, NLP4ITA, pages 1-8, 2012.  ... 
doi:10.5281/zenodo.2593328 fatcat:jqzdbcgskveorcml7ogqwkzuue

The ways of referential deficiency: Impersonal on and its kin [article]

Milan Rezac, Mélanie Jouitteau
2016 Zenodo  
The work builds on the analysis of on and its kin in Cinque (1988), Chierchia (1995b), Egerland (2003b), Kayne (2010), and explores them in the Principles-and-Parameters approach to syntax and the "situated  ...  to definites (Heim 1991, 2011; Heim 1982, Elbourne 2013), and minimal pronoun anaphora (Kratzer 2009).  ...  Near-absence of content in on at first sight suggests another approach to on. On is a way of coding an argument. One well-understood way of coding arguments is by DPs.  ... 
doi:10.5281/zenodo.5823634 fatcat:v4ie5x7xube2jokphozx4cvaau

GeBioToolkit: Automatic Extraction of Gender-Balanced Multilingual Corpus of Wikipedia Biographies [article]

Marta R. Costa-jussà, Pau Li Lin, Cristina España-Bonet
2019 arXiv   pre-print
While our toolkit is customizable to any number of languages (and different domains), in this work we present a corpus of 2,000 sentences in English, Spanish and Catalan, which has been post-edited by  ...  native speakers to become a high-quality dataset for machinetranslation evaluation.  ...  Acknowledgments The authors want to thank Jordi Armengol, Magdalena Biesialska, Casimiro Carrino, Noe Casas, Guillem Cortès, Carlos Escolano, Gerard Gallego and Bardia Rafieian for  ... 
arXiv:1912.04778v1 fatcat:mf27cv7shzalta4yy432tcnfdy

Deep Cross-Lingual Coreference Resolution for Less-Resourced Languages: The Case of Basque

Gorka Urbizu, Ander Soraluze, Olatz Arregi
2019 Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference   unpublished
With this approach, the system learns from a bigger English corpus, using cross-lingual embeddings, to perform the coreference resolution for Basque.  ...  In this paper, we present a cross-lingual neural coreference resolution system for a lessresourced language such as Basque.  ...  We thank the three anonymous reviewers whose comments and suggestions contributed to improve this work.  ... 
doi:10.18653/v1/w19-2806 fatcat:vxpjbqojb5a6lkqvv5cwtpbreu

UC Merced Proceedings of the Annual Meeting of the Cognitive Science Society Title Cohesion Grading Decisions in a Summary Evaluation Environment: A Machine Learning Approach Permalink Publication Date Cohesion Grading Decisions in a Summary Evaluation Environment: A Machine Learning Approach

Iraide Zipitria, Basilio Sierra, Ana Arruarte, Iraide Zipitria, Basilio Sierra, Ana Arruarte, Jon Elorriaga, Sierra, Arruarte
2012 Proceedings of the Annual Meeting of the Cognitive Science Society   unpublished
For this purpose, 45 basic cohesion measures are compared to overall human cohesion grades. Machine Learning techniques are used to select the best combination for cohesion grading.  ...  The work presented in this paper has been carried out in the context of a summary writing environment provided with automatic grading.  ...  Acknowledgments This work is supported by the University of The Basque Country (EHU09/09), the Spanish Ministry of Education (TIN2009-14380), and the Basque Government (IT421-10).  ... 

Exploring Shakespeare's Sonnets with SPARSAR

Rodolfo Delmonte
2016 Linguistics and Literature Studies  
In a previous paper we discussed how colours may be used appropriately to account for the overall underlying mood and attitude expressed in the poem, whether directed to sadness or to happiness.  ...  In this case, the aim is trying to discover what features of a poem characterize most popular sonnets.  ...  When fully coherent and complete predicate argument structures have been built, pronominal binding and anaphora resolution algorithms are fired.  ... 
doi:10.13189/lls.2016.040110 fatcat:wuzykekyyraa3iekgfr2z2oyii

Statistical Parsing by Machine Learning from a Classical Arabic Treebank [article]

Kais Dukes
2015 arXiv   pre-print
To test this hypothesis, two approaches are compared. As a reference, a pure dependency parser is adapted using graph transformations, resulting in an 87.47% F1-score.  ...  A central argument of this thesis is that using a hybrid representation closely aligned to traditional grammar leads to improved parsing for Arabic.  ...  The question that divides us is whether it is crazy enough to have a chance of being correct. -Niels Bohr  ... 
arXiv:1510.07193v1 fatcat:mkx5gtgehrgfjjy5xmwowxgasq

Linked open data to represent multilingual poetry collections. A proposal to solve interoperability issues between poetic repertoires

Elena González-Blanco, Gimena del Rio, Clara Martínez Cantón
2016 Zenodo  
Th is paper describes the creation of a poetic ontology in order to use it as a basis to link different databases and projects w orking on metrics and poetry.  ...  Its final objective is to interconnect, reuse and locate data disseminated through poetic repertoi res, in order to boost int eroperability among them.  ...  In 2012, the first author continued his research on OLiA in the context of PostDoc fellowship at the Information Sciences Institute of the University of Southern California funded by the German Academic  ... 
doi:10.5281/zenodo.2551595 fatcat:4nbzl534ebgnbort742fhfoqam
« Previous Showing results 1 — 15 out of 39 results