645 Hits in 5.1 sec

BART: A Multilingual Anaphora Resolution System

Samuel Broscheit, Massimo Poesio, Simone Paolo Ponzetto, Kepa Joseba Rodríguez, Lorenza Romano, Olga Uryupina, Yannick Versley, Roberto Zanoli
2010 International Workshop on Semantic Evaluation  
For the SemEval task 1 on Coreference Resolution, BART runs have been submitted for German, English, and Italian. BART relies on a maximum entropy-based classifier for pairs of mentions.  ...  ., 2008 ) is a highly modular toolkit for coreference resolution that supports state-of-the-art statistical approaches and enables efficient feature engineering.  ...  Our effort represents the first steps towards building a freely available coreference resolution system for many languages.  ... 
dblp:conf/semeval/BroscheitPPRRUV10 fatcat:u2ngxgsgtvfathyo2syow3drw4

Translation- and Projection-Based Unsupervised Coreference Resolution for Polish [chapter]

Maciej Ogrodniczuk
2013 Lecture Notes in Computer Science  
Creating a coreference resolution tool for a new language is a challenging task due to substantial effort required by development of associated linguistic data, regardless of rule-based or statistical  ...  In this paper, we test the translation-and projection-based method for an inflectional language, evaluate the result on a corpus of general coreference and compare the results with state-of-the-art solutions  ...  ) and Stanford CoreNLP [9] , one of the best coreference resolution systems up to date, has been used for English mention detection and coreference resolution.  ... 
doi:10.1007/978-3-642-38634-3_14 fatcat:6iv4wb2mejfybkjmud5qk6j5g4

The News People Search Task at EVALITA 2011: Evaluating Cross-Document Coreference Resolution of Named Person Entities in Italian News [chapter]

Luisa Bentivogli, Alessandro Marchetti, Emanuele Pianta
2013 Lecture Notes in Computer Science  
The NePS Task aims at evaluating crossdocument coreference resolution of person entities in Italian news and consists of clustering a set of Italian newspaper articles that mention a person name according  ...  The motivation behind the task, the dataset used for the evaluation and the results obtained are described and discussed.  ...  evaluation framework for crossdocument coreference resolution systems working on Italian.  ... 
doi:10.1007/978-3-642-35828-9_14 fatcat:tfpa5qmgr5ca5jdbro54cernny

TANL-1: Coreference Resolution by Parse Analysis and Similarity Clustering

Giuseppe Attardi, Maria Simi, Stefano Dei Rossi
2010 International Workshop on Semantic Evaluation  
Our submission to the Semeval 2010 task on coreference resolution in multiple languages is based on parse analysis and similarity clustering.  ...  The system uses a binary classifier, based on Maximum Entropy, to decide whether or not there is a relationship between each pair of mentions extracted from a textual document.  ...  According to Ng (2005) , most learning based coreference systems can be defined by four elements: the learning algorithm used to train the coreference classifier, the method of creating training instances  ... 
dblp:conf/semeval/AttardiSR10 fatcat:jcnrmh5n5naypfj43s5ipvpcgq

ELECTRA for Neural Coreference Resolution in Italian

Raffaele Guarasci, Aniello Minutolo, Emanuele Damiano, Giuseppe De Pietro, Hamido Fujita, Massimo Esposito
2021 IEEE Access  
CONCLUSION AND FUTURE WORK In this paper a coreference resolution system for the Italian language has been presented.  ...  ELECTRA, and a novel Italian corpus to make a robust and efficient coreference resolution system for the Italian language, ii) replacing ELECTRA with BERT in order to compare their performance and assess  ...  on virtual doctor systems for medical applications.  ... 
doi:10.1109/access.2021.3105278 fatcat:ccoke5bvlfc3lpokecxfsvmgsm

Evalita 2011: Anaphora Resolution Task [chapter]

Olga Uryupina, Massimo Poesio
2013 Lecture Notes in Computer Science  
This paper discusses the Anaphora Resolution task proposed as a track at the Evalita-2011 evaluation campaign for the Italian language.  ...  The annotation guidelines have been designed to cover a large variety of linguistic phenomena related to anaphora/coreference.  ...  information for Italian might be less accurate and therefore, a coreference resolution system should be able to cope with a noisy input.  ... 
doi:10.1007/978-3-642-35828-9_16 fatcat:2biyuid5bjfvvmdkngm3h6kumu

LiMoSINe Pipeline: Multilingual UIMA-based NLP Platform

Olga Uryupina, Barbara Plank, Gianni Barlacchi, Francisco J Valverde-Albacete, Manos Tsagkias, Antonio Uva, Alessandro Moschitti
2016 Proceedings of ACL-2016 System Demonstrations  
The system is available in two versions: a standalone distribution enables design and optimization of userspecific sub-modules, whereas a server-client distribution allows for straightforward highperformance  ...  We present a robust and efficient parallelizable multilingual UIMA-based platform for automatically annotating textual inputs with different layers of linguistic description, ranging from surface level  ...  Coreference Resolution. A coreference model for BART has been trained on the Italian portion of the SemEval-2010 Task 1 dataset (Uryupina and Moschitti, 2014) .  ... 
doi:10.18653/v1/p16-4027 dblp:conf/acl/UryupinaPBVTUM16 fatcat:tbxesxzcx5emxallenvvosjzyq

COREA: Coreference Resolution for Extracting Answers for Dutch [chapter]

Iris Hendrickx, Gosse Bouma, Walter Daelemans, Véronique Hoste
2012 Essential Speech and Language Technology for Dutch  
Coreference resolution is essential for the automatic interpretation of text.  ...  In this chapter we report on the development and evaluation of an automatic system for the robust resolution of referential relations in text.  ...  Acknowledgements We would like to thank Tim Van de Cruys for sharing his data sets of semantic clusters.  ... 
doi:10.1007/978-3-642-30910-6_7 dblp:series/tanlp/HendrickxBDH13 fatcat:2qxsacqf4vfhhmwkcwecg2v4nu

Instance Sampling for Multilingual Coreference Resolution

Desislava Zhekova
2011 Recent Advances in Natural Language Processing  
In this paper we investigate the effect of downsampling negative training instances on a multilingual memory-based coreference resolution approach.  ...  Our experiments show that downsampling negative training examples does not improve the overall system performance for most targeted languages and that the various evaluation metrics do not show a significantly  ...  coreference resolution system.  ... 
dblp:conf/ranlp/Zhekova11 fatcat:7dcteiubm5ai7gph5tccjrkxle

Coreference Resolution for Morphologically Rich Languages. Adaptation of the Stanford System to Basque

Ander Soraluze, Olatz Arregi, Xabier Arregi, Arantza Díaz de Ilarraza
2015 Revista de Procesamiento de Lenguaje Natural (SEPLN)  
We expect that the incorporation of new Basque-oriented treatments into the system will improve the overall scores.  ...  Our final goal is to create a robust end-to-end coreference resolution system for the Basque language.  ...  Related Work The first coreference resolution systems were designed for English; nowadays, however, many conferences focus on multilingual coreference resolution.  ... 
dblp:journals/pdln/SoraluzeAAI15 fatcat:nacj2vlaxzhy5e6noopf2nl2ca

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.  ...  The contribution of each sieve is analysed concluding that morphology is essential for agglutinative languages to obtain good performance in coreference resolution.  ...  We thank the anonymous reviewers for their extensive reviews. Author Contributions Investigation: Ander Soraluze.  ... 
doi:10.1371/journal.pone.0221801 pmid:31513627 pmcid:PMC6742394 fatcat:bwfi3a54bbgzhbu56n5dzys3ay

Coreference Reasoning in Machine Reading Comprehension [article]

Mingzhu Wu, Nafise Sadat Moosavi, Dan Roth, Iryna Gurevych
2021 arXiv   pre-print
We propose a methodology for creating MRC datasets that better reflect the challenges of coreference reasoning and use it to create a sample evaluation set.  ...  Coreference resolution is essential for natural language understanding and has been long studied in NLP.  ...  The first author of the paper is supported by a scholarship from Technical University of Darmstadt.  ... 
arXiv:2012.15573v2 fatcat:lxmoeb375neqjmvq6eaaq6zz4u

Event and Entity Coreference Across Five Languages: Effects of Context and Referring Expression

Luca Bevacqua, Sharid Loáiciga, Hannah Rohde, Christian Hardmeier
2021 Dialogue and Discourse  
Here we extend this work via a comparison across five languages (English, French, German, Italian, and Spanish).  ...  Our results show widely consistent, not categorical biases across languages: entity coreference is favoured for personal pronouns and event coreference for demonstratives.  ...  Acknowledgements Hannah Rohde was supported by a Leverhulme Trust Prize in Languages & Literatures. Christian Hardmeier was supported by the Swedish Research Council under grant 2017-930.  ... 
doi:10.5210/dad.2021.207 fatcat:zpv5mn3pmbg2zgwcr5nmsiyq3y

Coreference Resolution: Toward End-to-End and Cross-Lingual Systems

André Ferreira Cruz, Gil Rocha, Henrique Lopes Cardoso
2020 Information  
Finally, we discussed the main challenges and open issues faced by coreference resolution systems.  ...  The task of coreference resolution has attracted considerable attention in the literature due to its importance in deep language understanding and its potential as a subtask in a variety of complex natural  ...  Despite the continuous improvements over the years, a variety of challenges need to be addressed in order to create a truly domain-agnostic coreference resolution system.  ... 
doi:10.3390/info11020074 fatcat:jp4sajikina5noobeomccaamaa

Annotated Corpora and Annotation Tools [chapter]

Massimo Poesio, Sameer Pradhan, Marta Recasens, Kepa Rodriguez, Yannick Versley
2016 Anaphora Resolution  
In this Chapter we review the currently available corpora to study anaphoric interpretation, and the tools that can be used to create new ones.  ...  Acknowledgements This work was supported in part by a PhD studentship offered by Cogito / Expert Systems (Kepa Rodriguez), in part by the LIVEMEMORIES project (Poesio), and in part by the SENSEI project  ...  To this end, new datasets were created which, in the case of coreference, were the first corpora of any size available for training and evaluating coreference resolution systems.  ... 
doi:10.1007/978-3-662-47909-4_4 dblp:series/tanlp/PoesioPRRV16 fatcat:4dnly5kz6zar7bfboduulhu66a
« Previous Showing results 1 — 15 out of 645 results