Roberto Basili | "Tor Vergata" University of Rome (original) (raw)

Papers by Roberto Basili

Research paper thumbnail of Towards Compositional Tree Kernels

Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014 9-11 December 2014, Pisa

Research paper thumbnail of A context based model for Sentiment Analysis in Twitter for the Italian language

Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014 9-11 December 2014, Pisa, 2014

Research paper thumbnail of A Multiple Kernel Approach for Twitter Sentiment Analysis in Italian

Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014 9-11 December 2014, Pisa, 2014

Research paper thumbnail of The first italian conference on computational linguistic

Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014 9-11 December 2014, Pisa, 2014

Research paper thumbnail of A Language Independent Method for Generating Large Scale Polarity Lexicons

Sentiment Analysis systems aims at detecting opinions and sentiments that are expressed in texts.... more Sentiment Analysis systems aims at detecting opinions and sentiments that are expressed in texts. Many approaches in literature are based on resources that model the prior polarity of words or multi-word expressions, i.e. a polarity lexicon. Such resources are defined by teams of annotators, i.e. a manual annotation is provided to associate emotional or sentiment facets to the lexicon entries. The development of such lexicons is an expensive and language dependent process, making them often not covering all the linguistic sentiment phenomena. Moreover, once a lexicon is defined it can hardly be adopted in a different language or even a different domain. In this paper, we present several Distributional Polarity Lexicons (DPLs), i.e. large-scale polarity lexicons acquired with an unsupervised methodology based on Distributional Models of Lexical Semantics. Given a set of heuristically annotated sentences from Twitter, we transfer the sentiment information from sentences to words. The ...

Research paper thumbnail of Developing a large scale FrameNet for Italian: the IFrameNet experience

Proceedings of the Fourth Italian Conference on Computational Linguistics CLiC-it 2017, 2017

Research paper thumbnail of On the Readability of Kernel-based Deep Learning Models in Semantic Role Labeling Tasks over Multiple Languages

Italian Journal of Computational Linguistics, 2019

Research paper thumbnail of Monitoring Adolescents’ Distress using Social Web data as a Source: the InsideOut Project

Proceedings of the Fourth Italian Conference on Computational Linguistics CLiC-it 2017

Research paper thumbnail of Supervised semantic relation mining from linguistically noisy text documents

International Journal on Document Analysis and Recognition (IJDAR), 2010

Research paper thumbnail of Verb subcategorization kernels for automatic semantic labeling

Proceedings of the ACL-SIGLEX Workshop on Deep Lexical Acquisition - DeepLA '05, 2005

Research paper thumbnail of Knowledge-based multilingual document analysis

COLING-02 on SEMANET building and using semantic networks -, 2002

Research paper thumbnail of Semantic convolution kernels over dependency trees

Proceedings of the 20th ACM international conference on Information and knowledge management, 2011

Research paper thumbnail of A "not-so-shallow" parser for collocational analysis

Proceedings of the 15th conference on Computational linguistics -, 1994

Research paper thumbnail of EvalIta 2011: The Frame Labeling over Italian Texts Task

Lecture Notes in Computer Science, 2013

Research paper thumbnail of Engineering of syntactic features for shallow semantic parsing

Proceedings of the ACL Workshop on Feature Engineering for Machine Learning in Natural Language Processing - FeatureEng '05, 2005

Research paper thumbnail of Cross-Language Frame Semantics Transfer in Bilingual Corpora

Lecture Notes in Computer Science, 2009

Research paper thumbnail of Parsing engineering and empirical robustness

Natural Language Engineering, 2002

Robustness has been traditionally stressed as a general desirable property of any computational m... more Robustness has been traditionally stressed as a general desirable property of any computational model and system. The human NL interpretation device exhibits this property as the ability to deal with odd sentences. However, the difficulties in a theoretical explanation of robustness within the linguistic modelling suggested the adoption of an empirical notion. In this paper, we propose an empirical definition of robustness based on the notion of performance. Furthermore, a framework for controlling the parser robustness in the design phase is presented. The control is achieved via the adoption of two principles: the modularisation, typical of the software engineering practice, and the availability of domain adaptable components. The methodology has been adopted for the production of CHAOS, a pool of syntactic modules, which has been used in real applications. This pool of modules enables a large validation of the notion of empirical robustness, on the one side, and of the design met...

Research paper thumbnail of Tree Kernels for Semantic Role Labeling

Computational Linguistics, 2008

The availability of large scale data sets of manually annotated predicate-argument structures has... more The availability of large scale data sets of manually annotated predicate-argument structures has recently favored the use of machine learning approaches to the design of automated semantic role labeling (SRL) systems. The main research in this area relates to the design choices for feature representation and for effective decompositions of the task in different learning models. Regarding the former choice, structural properties of full syntactic parses are largely employed as they represent ways to encode different principles suggested by the linking theory between syntax and semantics. The latter choice relates to several learning schemes over global views of the parses. For example, re-ranking stages operating over alternative predicate-argument sequences of the same sentence have shown to be very effective. In this article, we propose several kernel functions to model parse tree properties in kernel-based machines, for example, perceptrons or support vector machines. In particul...

Research paper thumbnail of Evaluating a Robust Parser for Italian

Research paper thumbnail of Adaptive parsing for time-constrained tasks

Research paper thumbnail of Towards Compositional Tree Kernels

Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014 9-11 December 2014, Pisa

Research paper thumbnail of A context based model for Sentiment Analysis in Twitter for the Italian language

Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014 9-11 December 2014, Pisa, 2014

Research paper thumbnail of A Multiple Kernel Approach for Twitter Sentiment Analysis in Italian

Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014 9-11 December 2014, Pisa, 2014

Research paper thumbnail of The first italian conference on computational linguistic

Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014 9-11 December 2014, Pisa, 2014

Research paper thumbnail of A Language Independent Method for Generating Large Scale Polarity Lexicons

Sentiment Analysis systems aims at detecting opinions and sentiments that are expressed in texts.... more Sentiment Analysis systems aims at detecting opinions and sentiments that are expressed in texts. Many approaches in literature are based on resources that model the prior polarity of words or multi-word expressions, i.e. a polarity lexicon. Such resources are defined by teams of annotators, i.e. a manual annotation is provided to associate emotional or sentiment facets to the lexicon entries. The development of such lexicons is an expensive and language dependent process, making them often not covering all the linguistic sentiment phenomena. Moreover, once a lexicon is defined it can hardly be adopted in a different language or even a different domain. In this paper, we present several Distributional Polarity Lexicons (DPLs), i.e. large-scale polarity lexicons acquired with an unsupervised methodology based on Distributional Models of Lexical Semantics. Given a set of heuristically annotated sentences from Twitter, we transfer the sentiment information from sentences to words. The ...

Research paper thumbnail of Developing a large scale FrameNet for Italian: the IFrameNet experience

Proceedings of the Fourth Italian Conference on Computational Linguistics CLiC-it 2017, 2017

Research paper thumbnail of On the Readability of Kernel-based Deep Learning Models in Semantic Role Labeling Tasks over Multiple Languages

Italian Journal of Computational Linguistics, 2019

Research paper thumbnail of Monitoring Adolescents’ Distress using Social Web data as a Source: the InsideOut Project

Proceedings of the Fourth Italian Conference on Computational Linguistics CLiC-it 2017

Research paper thumbnail of Supervised semantic relation mining from linguistically noisy text documents

International Journal on Document Analysis and Recognition (IJDAR), 2010

Research paper thumbnail of Verb subcategorization kernels for automatic semantic labeling

Proceedings of the ACL-SIGLEX Workshop on Deep Lexical Acquisition - DeepLA '05, 2005

Research paper thumbnail of Knowledge-based multilingual document analysis

COLING-02 on SEMANET building and using semantic networks -, 2002

Research paper thumbnail of Semantic convolution kernels over dependency trees

Proceedings of the 20th ACM international conference on Information and knowledge management, 2011

Research paper thumbnail of A "not-so-shallow" parser for collocational analysis

Proceedings of the 15th conference on Computational linguistics -, 1994

Research paper thumbnail of EvalIta 2011: The Frame Labeling over Italian Texts Task

Lecture Notes in Computer Science, 2013

Research paper thumbnail of Engineering of syntactic features for shallow semantic parsing

Proceedings of the ACL Workshop on Feature Engineering for Machine Learning in Natural Language Processing - FeatureEng '05, 2005

Research paper thumbnail of Cross-Language Frame Semantics Transfer in Bilingual Corpora

Lecture Notes in Computer Science, 2009

Research paper thumbnail of Parsing engineering and empirical robustness

Natural Language Engineering, 2002

Robustness has been traditionally stressed as a general desirable property of any computational m... more Robustness has been traditionally stressed as a general desirable property of any computational model and system. The human NL interpretation device exhibits this property as the ability to deal with odd sentences. However, the difficulties in a theoretical explanation of robustness within the linguistic modelling suggested the adoption of an empirical notion. In this paper, we propose an empirical definition of robustness based on the notion of performance. Furthermore, a framework for controlling the parser robustness in the design phase is presented. The control is achieved via the adoption of two principles: the modularisation, typical of the software engineering practice, and the availability of domain adaptable components. The methodology has been adopted for the production of CHAOS, a pool of syntactic modules, which has been used in real applications. This pool of modules enables a large validation of the notion of empirical robustness, on the one side, and of the design met...

Research paper thumbnail of Tree Kernels for Semantic Role Labeling

Computational Linguistics, 2008

The availability of large scale data sets of manually annotated predicate-argument structures has... more The availability of large scale data sets of manually annotated predicate-argument structures has recently favored the use of machine learning approaches to the design of automated semantic role labeling (SRL) systems. The main research in this area relates to the design choices for feature representation and for effective decompositions of the task in different learning models. Regarding the former choice, structural properties of full syntactic parses are largely employed as they represent ways to encode different principles suggested by the linking theory between syntax and semantics. The latter choice relates to several learning schemes over global views of the parses. For example, re-ranking stages operating over alternative predicate-argument sequences of the same sentence have shown to be very effective. In this article, we propose several kernel functions to model parse tree properties in kernel-based machines, for example, perceptrons or support vector machines. In particul...

Research paper thumbnail of Evaluating a Robust Parser for Italian

Research paper thumbnail of Adaptive parsing for time-constrained tasks