Table des matières

Roberto Basili, Malvina Nissim et Giorgio Satta

• Conference and Programme Chairs
• Area Chairs
• Local Organisers
• Reviewers

Matteo Amore

• 1 Introduzione
• 1.1 Intrasitività scissa in italiano
• 1.2 Obiettivo di ricerca
• 1.3 Neologismi
• 2 Metodologia
• 2.1 Scelta del corpus
• 2.2 Creazione della lista
• 2.3 Ricerca su itTenTen
• 2.4 Analisi morfosintattica
• 3 Risultati
• 3.1 Comportamento sintattico
• 3.2 Selezione dell’ausiliare
• 4 Conclusioni

Gianni Barlacchi, Bruno Lepri et Alessandro Moschitti

• 1 Introduction
• 2 Related Work
• 3 Land Description Data
• 3.1 Land Use
• 3.2 Point-Of-Interest
• 4 Structural Models
• 4.1 Point-of-interests Features
• 4.2 Geographical Tree Kernel
• 5 Experiments and Results
• 5.1 Results for Land Use Classification
• 6 Conclusions
• Acknowledgments

Angelo Basile, Tommaso Caselli et Malvina Nissim

• 1 Introduction and Background
• 2 Data and Methodology
• 3 Experiments
• 4 Conclusions and Future Work
• Acknowledgments

Pierpaolo Basile, Giovanni Semeraro et Pierluigi Cassotti

• 1 Background and Motivation
• 2 Methodology
• 3 Evaluation
• 3.1 PoS tagging of Tweets
• 3.2 NER Task
• 3.3 Super Sense Tagging
• 4 Conclusions and Future Work
• Acknowledgments

Roberto Basili, Valentina Bellomaria, Niels J. Bugge et al.

• 1 Introduction
• 2 The InsideOut Web Platfrom
• 3 Distress Characterization: The semantic modeling
• 4 The InsideOut Annotated Corpus
• 5 Exploratory Evaluation
• 6 Conclusions

Alessia Bianchini, Francesco Tarasconi, Raffaella Ventaglio et al.

• 1 Why Pragmatics Matters in Chatbots
• 2 Intent Understanding in Practice
• 3 System Design and Architecture
• 4 Conclusions and Further Work

Yuri Bizzoni, Marco S. G. Senaldi et Alessandro Lenci

• 1 Introduction
• 2 Related Work
• 3 Dataset
• 3.1 Target expressions extraction
• 3.2 Building target vectors
• 3.3 Gold standard idiomaticity judgments
• 4 Classifier
• 5 Evaluation
• 5.1 Verb-Noun
• 5.2 Adjective-Noun
• 5.3 Joint training
• 5.4 Vector composition
• 6 Error Analysis
• 7 Discussion and Conclusions

Daniele Bonadiman, Giuseppe Castellucci, Andrea Favalli et al.

• 1 Introduction
• 2 Related Work
• 3 Application Scenario
• 3.1 Focused Problem Description
• 3.2 Data Description
• 4 Our Neural Network Approach
• 5 Experiments
• 5.1 Setup
• 5.2 Results on English Data
• 5.3 Results on Italian Data
• 5.4 Discussion of the Results
• 6 Conclusions

Alessandro Bondielli, Lucia C. Passaro et Alessandro Lenci

• 1 Introduction
• 2 Resources
• 2.1 Italian ANEW
• 2.2 ItEM
• 3 From fine-grained Emotion Values to Polarity
• 3.1 Polynomial regression
• 3.2 Logistic regression
• 4 Results and discussion
• 5 Conclusions and ongoing research

Peter Bourgonje, Yulia Grishina et Manfred Stede

• 1 Introduction
• 1.1 Background: Connectives
• 1.2 Motivation and contribution
• 2 Lexicons: DiMLex and LICo
• 3 Exploiting a parallel corpus
• 3.1 Method: Iterative lookup
• 3.2 Results
• 3.2.1 German–Italian
• 3.2.2 Italian–German
• 4 Related work
• 5 Toward a bilingual connective database
• 5.1 Connective mappings
• 5.2 From connectives to phrases
• 5.3 Senses and their distributions
• 6 Summary
• Acknowledgments

Roberto Basili, Silvia Brambilla, Danilo Croce et al.

• 1 Introduction
• 2 The development of the large scale IFrameNet resource
• 2.1 Integrating corpus processing and lexical analysis for populating IFrameNet
• 2.2 The development cycle
• 3 Status of the Project and Perspective Views
• 3.1 Empirical Investigation: First Lexical Analysis and Validation
• 3.2 Empirical Investigation: Current Results

Marco Budassi, Eleonora Litta et Marco Passarotti

• 1 Introduction
• 2 Lemlat and Du Cange
• 3 Nouns Ending in -io
• 4 Methodology
• 5 Distribution of -io Nouns in Latin
• 6 General Discussion
• 7 Conclusions and Future Work

Lucia Busso et Gianmarco Vignozzi

• 1 Introduction
• 2 Films, language and gender
• 3 Data and corpus driven analysis
• 4 Results
• 5 Conclusions

Franco Alberto Cardillo, Marcello Ferro, Claudia Marzi et al.

• 1 Introduction
• 2 The cell-filling problem
• 2.1 Methods and materials
• 3 Results and discussion

Héctor Cerezo-Costas, Manuela Martín-Vicente et F.J. González-Castaño

• 1 Introduction
• 2 Related Work
• 3 Approach
• 4 Experiments
• 5 Results and conclusion
• Acknowledgments

Alessandra Cervone, Evgeny A. Stepanov, Fabio Celli et al.

• 1 Introduction
• 2 Related Works
• 3 Data Set
• 4 Methodology
• 5 Results and Discussion
• 6 Conclusion
• Acknowledgments

Cristiano Chesi

• 1 Introduction
• 2 Parsing with Minimalist Grammars
• 2.1 The “similarity” problem
• 3 A processing-friendly proposal
• 3.1 Parsing cleft structures with PMGs
• 4 Explaining the “similarity” problem in terms of cue-based feature retrieval
• 5 Conclusion

Alessandra Teresa Cignarella, Cristina Bosco et Viviana Patti

• 1 Introduction
• 2 Data collection
• 3 A multi-layered annotation scheme
• 4 Annotation and Disagreement
• 4.1 Disagreement Analysis
• 5 Discussion
• 6 Conclusions and future work
• Acknowledgements

Andrea Cimino, Martijn Wieling, Felice Dell’Orletta et al.

• 1 Introduction
• 2 Model training and feature ranking
• 3 Typology of Features
• 4 Experiments
• 4.1 Experimental Setup
• 4.2 Replication
• 5 Results
• 5.1 Genre Classification Results
• 5.2 Feature Ranking Results
• 6 Conclusion
• Acknowledgements

Claudia Roberta Combei

• 1 Introduction
• 2 Motivations
• 3 Data Collection
• 3.1 Speakers’ recruitment
• 3.2 Experimental protocol
• 3.3 Speech modalities
• 4 Description of CorAIt
• 4.1 Speakers’ statistics
• 4.2 Speech samples
• 4.3 Webapp architecture
• 4.4 Front-end presentation
• 5 Conclusion and future work
• 6 Acknowledgements

Giorgia Conte, Cristina Bosco et Alessandro Mazzei

• 1 Introduction
• 2 The Theoretical Status of the Adjective in the Nominal Phrase
• 2.1 A hierarchy of the Descriptive Adjectives
• 3 Extracting Adjectives from Corpora
• 3.1 PoSTWITA
• 3.2 UD-it
• 3.3 Discussion of Results
• 4 Ordering adjectives in SimpleNLG-IT
• 5 Conclusion and future work

Maria De Martino, Azzurra Mancuso et Alessandro Laudanna

• 1. Introduzione
• 1.1 Organizzazione della Banca-Dati
• 2. Variabili Formali e Distribuzionali
• 3. Giudizi su Variabili Soggettive
• 4. Variabili Morfologiche e MorfoFonologiche
• 5. Variabili Semantiche
• 6. Variabili Sintattiche
• 7. Misure Comportamentali

Francesca Della Moretta, Elisabetta Jezek, Anna Feltracco et al.

• 1 Introduction
• 2 Overview of the T-PAS resource
• 3 Annotating Semantic Types
• 4 Results of the Pilot Annotation
• 4.1 Inter-annotator Agreement
• 5 Discussion
• 5.1 Discussion: Argument Tagging
• 5.2 Discussion: Semantic Type Tagging
• 6 Conclusions

Maria Pia di Buono et Jan Šnajder

• 1 Introduction
• 2 Related Work
• 3 Data Description
• 4 Linguistic Features
• 5 Analysis and Results
• 5.1 Text Easability Features
• 5.2 Word Information
• 6 Conclusions and Future work
• Acknowledgments

Mattia A. Di Gangi et Federico Marcello

• 1 Introduction
• 2 State of the art
• 3 Using external word embeddings
• 4 Experimental setup
• 5 Results and Discussion
• 6 Conclusions
• Acknowledgments

Dario Di Mauro, Antonio Origlia et Francesco Cutugno

• 1 Introduction
• 2 Related works
• 3 Model
• 3.1 A Smart Entity
• 3.2 Model of PHASER
• 4 Navigation Problem
• 4.1 Perfect matching
• 4.2 Imperfect matching
• 5 Experiments and Results
• 6 Discussion
• 7 Conclusions

Giorgio Maria Di Nunzio, Federica Beghini, Federica Vezzani et al.

• 1 Introduction
• 1.1 Reproducible Research in IR and NLP
• 1.2 Contribution
• 2 R for Reproducible Research
• 2.1 Dataset
• 2.2 Pipeline for Data Cleaning
• 2.3 Classification rule
• 3 Experiments and Results
• 4 Final remarks and Future Work

Anna Feltracco, Bernardo Magnini et Elisabetta Jezek

• 1 Introduction
• 2 The Contrast Relation
• 3 Adopting the PDTB Schema
• 4 Contrast-Ita Bank
• 5 Inter Annotator Agreement
• 6 Conclusion and Further Work

Simona Frenda

• 1 Introduction
• 2 Related Work
• 3 Methodology
• 3.1 Corpora of tweets
• 3.2 Resources and Data Processing
• 4 Irony Detection Model
• 5 Discussion and Conclusions

Anastasia Giachanou, Francisco Rangel, Fabio Crestani et al.

• 1 Introduction
• 2 Related Work
• 3 Methodology
• 4 Experimental Setup
• 4.1 Dataset
• 4.2 Baselines
• 4.3 Experimental Settings
• 5 Results
• 6 Conclusions and Future Work

Emiliano Giovannetti, Davide Albanesi, Andrea Bellandi et al.

• 1 Introduction
• 2 Background
• 3 Methodology
• 4 Evaluation
• 5 Conclusions
• 6 Acknowledgment

Delia Irazú Hernández Farías, Irene Laganà, Viviana Patti et al.

• 1 Introduction
• 2 Our Methodology
• 2.1 Sentiment Analysis Resources
• 2.2 Qualitative Analysis of Benchmark Lexica
• 3 Lost in Translation: Impact of the Errors
• 4 Conclusions and Future Work
• Acknowledgements

Surafel M. Lakew, Mattia A. Di Gangi et Marcello Federico

• 1 Introduction
• 2 State of The Art
• 3 M-NMT for Low-resource Languages
• 4 Experimental setting
• 5 Results
• 5.1 Bilingual Vs. Multilingual
• 5.2 Pivoting using a Multilingual Model
• 6 Conclusions
• Acknowledgments

Alessandro Laudanna et Giulia Bracco

• 1 Introduction
• 2 Experiment 1
• 2.1 Method
• 2.2 Results and Discussion
• 3 Experiment 2
• 3.1 Method
• 3.2 Results and Discussion
• 4 General Discussion

Vincenzo Lombardo, Rossana Damiano et Antonio Pizzo

• 1 Introduction
• 2 Drama and annotation
• 3 The Drammar ontology
• 4 Crowdsourcing annotation of drama texts: the POP-ODE initiative
• 5 Conclusion

Caterina Masotti, Danilo Croce et Roberto Basili

• 1 Introduction
• 2 The Show and Tell Architecture
• 3 Automatic acquisition of a Corpus of Captions in Italian
• 4 Experimental Evaluation
• 5 Conclusions

Silvia Micheli et Eleonora Litta

• 1 Introduction: the Word Formation Latin lexicon
• 2 Latin compounding
• 3 Compounding in WFL
• 3.1 Word Formation Rules
• 3.2 Input and output lexical categories
• 3.3 Some caveats
• 4 Conclusions and future work

Anne-Lyse Minard, Manuela Speranza, Mohammed R. H. Qwaider et al.

Category-driven Selection Strategies for Active Learning

• 1 Introduction
• 2 Related Work
• 3 Experimental Setting
• 4 Selection Strategies
• 5 Results and Discussion
• 6 Application: Sanremo’s Ranking
• 7 Conclusion
• Acknowledgments

Ignazio Mauro Mirto et Emanuele Cipolla

• 1 Introduzione
• 2 Ambiguità
• 3 L’Algoritmo di Disambiguazione
• 3.1 Dei nel Complemento di Specificazione
• 3.2 Dei come Complemento Retto
• 3.3 Dei in frasi con essere come copula o con esserci
• 3.4 Dei in Soggetti o Oggetti di verbi transitivi e intransitivi
• 4 Conclusioni

Johanna Monti, Maria Pia di Buono et Federico Sangati

An annotated Corpus of Verbal Multiword Expressions in Italian

• 1 Introduction
• 2 State of the art in VMWE identification and annotation in Italian
• 3 Methodology
• 4 Italian VMWEs
• 5 Corpus and annotation task
• 5.1 PARSEME Italian VMWE corpus
• 5.2 Annotation environment
• 5.3 Annotation task
• 6 Results
• 7 Conclusion and Future Work
• Acknowledgments

Malvina Nissim et Paola Pietrandrea

• 1 Introduction and Background
• 2 Corpus
• 2.1 Approach to annotation
• 2.2 Procedure and final scheme
• 3 Evaluation
• 3.1 Alignment and Agreement
• 3.2 Results
• 4 Conclusions
• Acknowledgments

Ludovica Pannitto, Lavinia Salicchi et Alessandro Lenci

• 1 Introduction and related works
• 1.1 The pitfalls of the DIH
• 2 AHyDA: Smoothing the DIH
• 3 Experiments and Evaluation
• 3.1 Distributional Space
• 3.2 Data set
• 3.3 Evaluation
• 3.4 Results
• 4 Conclusion

Lucia C. Passaro, Alessandro Lenci et Anna Gabbolini

• 1 Introduction
• 2 The CoLingLab NER
• 3 A NER for PA Documents
• 3.1 The PA Corpus
• 3.2 Annotation
• 4 System Overview
• 4.1 System’s Performances
• 5 Towards a Relational Classifier for PA
• 6 Discussion
• 7 Conclusions and Ongoing Work
• Acknowledgments

Alessandro Maisto, Serena Pelosi, Simonetta Vietri et al.

• 1 Introduction
• 2 State of the Art on the Computational Treatment of Offensive Language
• 3 Lexical and Grammatical Resources
• 3.1 Simple Vulgar Words
• 3.2 Taboo Multiword Structures
• 4 Experiment and Evaluation
• 5 Conclusion

Marco Piersanti, Giulia Brandetti et Pierluigi Failla

• 1 Introduction
• 2 Related Works
• 3 Task Description
• 4 Experiments and Data
• 4.1 Data Description
• 4.2 Data Preprocessing
• 5 Model Description
• 5.1 Sentiment Analysis
• 5.2 Text Clustering
• 6 Results
• 7 Conclusions
• Acknowledgements

Fabio Poletto, Marco Stranisci, Manuela Sanguinetti et al.

• 1 Introduction
• 2 Related Work
• 3 Dataset Collection
• 4 Data Annotation: Designing and Applying the Schema
• 4.1 Agreement Analysis
• 5 Conclusion and Future Work
• Acknowledgments

Daniele Puccinelli, Silvia Demartini, Aris Piatti et al.

• 1 Introduction
• 2 Related Work and PoS taggers under test
• 3 The DFA-TIscrivo corpus
• 4 Methodology and Performance Analysis
• 5 Conclusion
• Acknowledgments

Mohammed R. H. Qwaider, Anne-Lyse Minard, Manuela Speranza et al.

• 1 Introduction
• 2 Related Work
• 3 Overall Description
• 4 Annotation Task Design
• 4.1 Annotation Procedure
• 4.2 Annotator’s Task
• 5 Annotation Monitoring
• 5.1 Progress Monitoring
• 5.2 Inter-Annotator Agreement Monitoring
• 5.3 Quality Monitoring
• 6 Applications and Further Extensions
• Acknowledgments

Andrea Amelio Ravelli, Lorenzo Gregori et Anna Feltracco

• 1 Introduction
• 2 The Resources
• 2.1 IMAGACT
• 2.2 T-PAS
• 3 The Mapping
• 4 Results and discussion
• 5 Future work
• 6 Conclusions

Marco Rovera, Federico Nanni, Simone Paolo Ponzetto et al.

• 1 Introduction and Motivation
• 2 Related Work
• 3 Dataset
• 4 Experiment
• 4.1 Test of existing automatic NERD tools
• 4.2 Methodology
• 5 Evaluation
• 6 Conclusions and Future Works

Alessio Salomoni

• 1 Introduction
• 2 Methodology
• 2.1 Data
• 2.2 Annotating a Gold Standard
• 2.3 Lemmatization
• 2.4 POS-Tagging
• 2.5 Dependency Parsing
• 2.6 Parsing in-depth Evaluation
• 3 Conclusion and Future Work

Randy Scansani, Marcello Federico et Luisa Bentivogli

• 1 Introduction
• 2 Previous work
• 3 Experimental Setup
• 3.1 Corpora
• 3.2 Terminology
• 3.3 Machine Translation System
• 4 Experimental results
• 5 Manual Evaluation
• 6 Conclusion and further work
• Ackowledgements

Rachele Sprugnoli, Sara Tonelli, Giovanni Moretti et al.

• 1 Introduction
• 2 Related Work
• 3 Corpus Description
• 4 Code-Mixing Detection
• 4.1 Experimental Setting
• 4.2 Evaluation
• 4.3 Post-processing
• 5 Discussion
• 6 Conclusions and Future Work

Irene Sucameli et Alessandro Lenci

• 1 Introduction
• 2 Related Works
• 3 Collecting PARAD-it
• 3.1 Target Selection
• 3.2 Data Elicitation
• 3.3 Results
• 3.4 Distributional Semantic Analysis of the Elicited Data
• 3 Conclusion

Sara Tonelli, Alessio Palmero Aprosio et Marco Mazzon

• 1 Introduction
• 2 Corpus analysis and Benchmark creation
• 3 Automated lexical simplification
• 3.1 The Lexenstein system
• 3.2 Experimental Setup
• 4 Evaluation
• 5 Conclusions
• Acknowledgments

Rocco Tripodi et Stefano Li Pira

• 1 Introduction
• 2 Related works
• 4 Evaluation
• 4.1 Experimental results
• 4.2 Error analysis
• 5 Conclusions
• Acknowledgments

Francesco Unguendoli, Giampaolo Cristadoro et Marco Beghelli

• 1 Motivazioni della ricerca
• 2 Gli n-grammi in ambito letterario
• 3 Verifiche sui testi musicali
• 4 Ambito d’indagine e obiettivo
• 5 Percorsi e metodi
• 6 Risultati
• 7 Conclusioni e prospettive

Antonio Uva, Valerio Storch, Casimiro Carrino et al.

• 1 Introduction
• 2 Related Work
• 3 The RGI application scenario
• 3.1 Task description
• 3.2 Data description
• 4 Our QA System
• 4.1 Question and Ticket Retrieval
• 4.2 Reranking Pipeline
• 5 Experiments
• 5.1 Results
• 6 Conclusions