Research Interests:
Research Interests:
Research Interests:
Research Interests:
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... 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 Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Computer Science, Artificial Intelligence, Natural Language Processing, Machine Translation, Syntax, and 9 moreStatistical Machine Translation, Semantics (Computer Science), Semantic Information, Parallel Corpora, Rule-Based Machine Translation, Rule Based, Target Language, Semantic Role Labeling, and Springer Ebooks
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... 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 Interests:
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... 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 Interests: Cognitive Science, Computer Science, Artificial Intelligence, Natural Language Processing, Machine Learning, and 10 moreComputational Linguistics, Support Vector Machines, Linguistics, Syntactic Parsing, Learning Model, Support vector machine, Structural Properties, Large Scale, Kernel Function, and Semantic Role Labeling
Research Interests:
Research Interests:
Tree Kernel Engineering in Semantic Role Labeling Systems Alessandro Moschitti and Daniele Pighin and Roberto Basili University of Rome, Tor Vergata {moschitti, basili}@ info. uniroma2. it daniele. pighin@ gmail. com Abstract Recent work... more
Tree Kernel Engineering in Semantic Role Labeling Systems Alessandro Moschitti and Daniele Pighin and Roberto Basili University of Rome, Tor Vergata {moschitti, basili}@ info. uniroma2. it daniele. pighin@ gmail. com Abstract Recent work on the design of ...
Research Interests:
Current NL parsers are expected to run with throughput rate suitable to satisfy time con-straints in real applications. The aim of the present work is, on the one hand, to investigate the effects of lexical information in a shallow... more
Current NL parsers are expected to run with throughput rate suitable to satisfy time con-straints in real applications. The aim of the present work is, on the one hand, to investigate the effects of lexical information in a shallow parsing environment, on the other hand, to study ...
Research Interests:
Dierent NLP applications have dierent eciency constraints (ie quality of the results and throughput) that reect on each core linguistic component. Syntactic processors are basic modules in some NLP application. A customization that... more
Dierent NLP applications have dierent eciency constraints (ie quality of the results and throughput) that reect on each core linguistic component. Syntactic processors are basic modules in some NLP application. A customization that permits the performance control of these ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Representation of statistical data is achieved by means of complex data structures. Such a complexity transfers directly to statistical data manipulations. Furthermore, the most meaningful statistical indicator resides in complex data... more
Representation of statistical data is achieved by means of complex data structures. Such a complexity transfers directly to statistical data manipulations. Furthermore, the most meaningful statistical indicator resides in complex data structures. Our work is focused on simplifying manipulations of statistical data structures by means of StEM (Statistical database Expert Manager), a knowledge-based kernel. StEM acts as a deductive query
Research Interests:
Research Interests:
@Book{FeatEng:2005, editor = {Eric Ringger}, title = {Proceedings of the ACL Workshop on Feature Engineering for Machine Learning in Natural Language Processing}, month = {June}, year = {2005}, address = {Ann Arbor, Michigan}, publisher =... more
@Book{FeatEng:2005, editor = {Eric Ringger}, title = {Proceedings of the ACL Workshop on Feature Engineering for Machine Learning in Natural Language Processing}, month = {June}, year = {2005}, address = {Ann Arbor, Michigan}, publisher = {Association for Computational Linguistics}, url = {http://www.aclweb.org/anthology/W/W05/W05-04} }
Research Interests:
Research Interests:
") Istituto di Studi suffa Ricerca e Docurnentazione Scientifiea (ISRDS) Consiglio Nazionale delle Rieerehe (CNR) / Via C. de Lollis 12 / 00185-ROMA (Italy) ^) Dipartimento di Ingegneria Elettronica Universit~ di Roma... more
") Istituto di Studi suffa Ricerca e Docurnentazione Scientifiea (ISRDS) Consiglio Nazionale delle Rieerehe (CNR) / Via C. de Lollis 12 / 00185-ROMA (Italy) ^) Dipartimento di Ingegneria Elettronica Universit~ di Roma II "For Vergata' / Via O. Raimondo / 00173-ROMA (Italy)
Research Interests:
The large-scale applicability of knowledge-based information access systems such as the ones based on Information Extraction techniques strongly depends on the possibility of automatically acquiring the large amount of knowledge required.... more
The large-scale applicability of knowledge-based information access systems such as the ones based on Information Extraction techniques strongly depends on the possibility of automatically acquiring the large amount of knowledge required. However, the basic assumption of the ...
Research Interests:
... di elaborazione dell'informazione di costruire e gestire rappresentazioni di crescente complessitá attraverso livelli di progressiva astrazione ha ... Ai processi indipendenti di gestione del sistema hardware si `e nel tempo... more
... di elaborazione dell'informazione di costruire e gestire rappresentazioni di crescente complessitá attraverso livelli di progressiva astrazione ha ... Ai processi indipendenti di gestione del sistema hardware si `e nel tempo sostituito quella di macchina astratta (hard-ware ...
Research Interests:
Research Interests:
Research Interests:
Abstract Automatic music transcription is a challenging topic in audio signal processing. It consists in transforming the musical content of audio data into a symbolic notation. The system discussed in this paper takes as input the sound... more
Abstract Automatic music transcription is a challenging topic in audio signal processing. It consists in transforming the musical content of audio data into a symbolic notation. The system discussed in this paper takes as input the sound of a recorded polyphonic piano music and it produces conventional musical representation as output. For each note event two main characteristics are considered: the attack instant and the pitch. Onset detection is obtained through a time-frequency representation of the audio signal. Note classification ...
Research Interests: Computer Science, Acoustics, Piano, Audio Signal Processing, Support Vector Machines, and 15 moreSpeech Recognition, Polyphony, MIDI, Music transcription, Support vector machine, Autocorrelation, Svm, Acoustical Engineering, Onset Detection, discrete Yang-Fourier transforms, Short Term Memory, Musical notation, Time Frequency Representation, Multiple Signal Classification, and Feature vector
Research Interests:
... Co-Training per la disambiguazione semantica di parole in testi liberi Relatore Correlatore Prof. Marco Liverani ... 1 Page 3. Sintesi In tutti questi campi l'informazione che si ottiene dipende fortemente dal significato che le... more
... Co-Training per la disambiguazione semantica di parole in testi liberi Relatore Correlatore Prof. Marco Liverani ... 1 Page 3. Sintesi In tutti questi campi l'informazione che si ottiene dipende fortemente dal significato che le parole assumono all'interno delle frasi, o pi`u in generale, ...
... QUINDI: rappresentare i vettori dei testi (colonne della matrice W) mediante vjS, significa combinare linearmente (mediante S) le righe (i termini ui) della base ortonormale data da U US e VS rappresentano le mappature di termini in V... more
... QUINDI: rappresentare i vettori dei testi (colonne della matrice W) mediante vjS, significa combinare linearmente (mediante S) le righe (i termini ui) della base ortonormale data da U US e VS rappresentano le mappature di termini in V e documenti in T nello spazio di ...
Research Interests:
... Additional Classification: J. Computer Applications J.5 ARTS AND HUMANITIES Subjects: Linguistics. General Terms: Theory. Collaborative Colleagues: Roberto Basili: colleagues. Maria-Teresa Pazienza: colleagues. Paola Velardi:... more
... Additional Classification: J. Computer Applications J.5 ARTS AND HUMANITIES Subjects: Linguistics. General Terms: Theory. Collaborative Colleagues: Roberto Basili: colleagues. Maria-Teresa Pazienza: colleagues. Paola Velardi: colleagues. ...