Table des matières

Cristina Bosco, Sara Tonelli et Fabio Massimo Zanzotto

Marco Angster

• 1. Introduction
• 2. Bolzano/Bozen Corpus
• 3. IMDI and <Actors>
• 4. Speakers in Komma and Kontatto projects
• 5. CMDI: a very customisable, but closed structure
• 6. Conclusion

Giuseppe Attardi, Vittoria Cozza et Daniele Sartiano

• 1. Introduction
• 2. Related Work
• 3. Negation and speculation detection
• 3.1 Scope Detection
• 3.2 Experiments
• 4. Conclusions

Giuseppe Attardi, Laura Gorrieri, Alessio Miaschi et al.

• 1. Introduction
• 2. Building Word Embeddings
• 2.1 Discriminative Word Embeddings
• 3. Deep Learning Architecture
• 4. Experiments
• 4.1 Lexicon
• 4.2 Classifier
• 4.3 Results
• 4.4 Related Work
• 5 Conclusions

Giuseppe Attardi, Simone Saletti et Maria Simi

• 1. Introduction
• 2. From ISDT to UD-it
• 2.1 Differences in annotation guidelines
• 2.2 Change of format
• 2.3 Corpus extension
• 3. Dependency parsers
• 3.1 DeSR
• 3.2 Turbo Parser
• 3.3 MATE Parser
• 4. Experiments
• 4.1 Evalita results on ISDT
• 4.2 Evalita dataset in UD 1.1
• 5. Training with additional data
• 5.1 Evalita dataset in UD 1.2
• 5.2 UD-it 1.1 dataset
• 5.3 UD-it 1.2 dataset
• 5.4 Parser efficiency
• 6. Conclusions

A. Barbagli, P. Lucisano, F. Dell’Orletta et al.

• 1. Introduzione
• 2. Corpus
• 3. Schema di Annotazione
• 4. CItA per

Pierpaolo Basile, Annalina Caputo et Giovanni Semeraro

• 1. Introduction
• 2. Dataset
• 3. DSM-TEL algorithm
• 4. Evaluation
• 5. Conclusion

Pierpaolo Basile, Valerio Basile, Malvina Nissim et al.

• 1. Introduction
• 2. Open Challenges
• 3. Task Description
• 3.1 Task 1 - Entity Detection and Linking
• 3.2 Task 2 - Message Level and Entity-Based Sentiment Analysis
• 4. Feasibility

Yuri Bizzoni, Riccardo Del Gratta, Federico Boschetti et al.

• 1. Introduction
• 2. Translation Mining through Semantic Spaces
• 2.1 Aligning long and literary-biased translations to the original text
• 2.2 Distributional Semantics
• 2.3 Semantic Spaces based on aligned corpora
• 2.4 Words and their translations tend to be neighbors
• 2.5 Parts of Speech Translations
• 2.6 Data Presentation and Some Results
• 2.7 AGWN: strenghtening bilingual links
• 2.8 CoPiWn! (CoPiWn!): supporting hypernym/hyponym relations
• 3. Conclusions and Future Work

Daniele Bonadiman, Aliaksei Severyn et Alessandro Moschitti

• 1. Introduction
• 2. Our DNN model for NER
• 2.1 Context Window Network
• 2.2 Our model
• 2.2.1 Recurrent Context Window Network
• 3 Experiments
• 3.1 Experimental setup
• 3.2 Results
• 4. Conclusion

Francis Bond et Giulia Bonansinga

• 1. Introduction
• 2. SemCor, a corpus made multilingual by sense projection
• 3. Preprocessing and requirements
• 4. Multilingual Sense Intersection
• 5. Evaluation and discussion
• 6. Conclusions

Dominique Brunato et Felice Dell’Orletta

• 1. Introduction
• 2. The corpus
• 2.1 Participants
• 2.2 Methodology
• 2.3 Oral data transcription
• 2.4 Linguistic annotation of errors
• 3. Preliminary explorations of the corpus
• 3.1 First results on linguistic structure
• 3.2 Analysis of the content
• 4. Conclusion

Elena Cabrio et Serena Villata

• 1. Introduction
• 2. BEGincs framework
• 2.1 Argumentation theory
• 2.2 Inconsistencies detection
• 3. Experimental setting
• 4. Concluding remarks

Giuseppe Castellucci, Danilo Croce et Roberto Basili

• 1. Introduction
• 2. Sentiment Analysis through Label Propagation over Contextual Graphs
• 2.1 Label Propagation Algorithms
• 2.2 Contextual Graph: a definition
• 3. Experimental Evaluation
• 3.1 Graph Construction
• 3.2 Experimental Results
• 4. Conclusion

Flavio Massimiliano Cecchini et Elisabetta Fersini

• 1. Introduction
• 2. Building the word graphs
• 2.1 A weighted Jaccard distance
• 2.2 Word clouds
• 3 The gangplank clustering algorithm
• 3.1 The algorithm
• 3.2 The labelling step
• 4. Evaluation on tweets
• 4.1 Data and tagging
• 4.2 Evaluation and results
• 5. Related work
• 6. Conclusions

Fabio Celli et Luca Polonio

• 1. Introduction and Background
• 2. Data and Method
• 3. Experiments and Results
• 4. Discussion and Conclusions

Francesca Chiusaroli

• 1. Introduzione
• 2. La dimensione nomenclaturista
• 3. La grammatica
• 4. Universalismo vs. relativismo
• 5. Testo letterario e frasario
• 6. Conclusioni

Giovanni Colavizza et Frédéric Kaplan

• 1. Introduction
• 2. Related work
• 3. Approach
• 4. Experiments
• 4.1 Text block detection
• 4.2 Citation extraction
• 4.3 Citation parsing
• 5. Conclusions and future work

Riccardo Del Gratta, Francesca Frontini, Monica Monachini et al.

• 1. Introduction
• 2. Metadata description
• 3. People and Resources: visualising networks
• 4. Conclusions and future works

Marilena Di Bari, Serge Sharoff et Martin Thomas

• 1. Introduction
• 2. Annotation scheme and corpus
• 3. Results of the annotation
• 4. Conclusions

Luigi Di Caro, Guido Boella, Alice Ruggeri et al.

• 1. Introduction and Background
• 2. A Semantic Distributional Hypothesis
• 2.1 Feasibility
• 2.2 Research Objectives
• 3. Project Architecture
• 3.1 Data Acquisition
• 3.2 Distributional Analysis of Semantics
• 3.3 Compositionality and reasoning
• 3.4 Extension of Semantic Resources
• 3.5 Multilingual Mapping
• 3.6 Exploitation
• 4. Conclusions

Paolo Dragone et Pierre Lison

• 1. Introduction
• 2. Background
• 3. Approach
• 3.1 Baseline
• 3.2 Extending the feature set
• 3.3 Active learning
• 4. Evaluation
• 5. Conclusion

Fabrizio Esposito, Pierpaolo Basile, Francesco Cutugno et al.

• 1. Introduction
• 2. Corpus Overview
• 3. Corpus Construction and Annotation
• 3.1 Construction and Structural Annotation
• 3.2 Linguistic Annotation
• 4. TRI on the CompWHoB Corpus
• 5. Conclusions

Fathi Fawi

• 1. Introduzione
• 2. Stato dell'arte
• 3. Progettazione del corpus
• 4. Descrizione del corpus
• 5. Costituzione e preparazione del corpus
• 6. Trattamento del corpus
• 6.1 Segmentazione
• 6.2 Tokenizzazione
• 6.3 Allineamento
• 6.4 Annotazione del corpus
• 7. Conclusione

Fathi Fawi et Rodolfo Delmonte

• 1. Introduction
• 2. Related works
• 3. The proposed approach
• 3.1 Morphological analysis
• 3.2 Create candidate terms
• 3.3 Statistical filter
• 3.3.1 Likelihood ratio
• 3.3.2 C-NC value
• 3.4 Identification of translation equivalents
• 4. Experiments and Results
• 4.1 The Corpus
• 4.2 Evaluation
• 5. Conclusion

Michele Filannino et Marilena Di Bari

• 1. Introduction
• 2. Background
• 3. The corpus
• 4. Experiments
• 4.1 Test corpora
• 4.2 Experimental setting
• 5 Results
• 6. Conclusions

Federico Giusfredi

• 1. Introduction
• 2. Expanding the tagset
• 2.1 Subordination and relative clauses
• 3. Lacunae and cruces
• 3.1 Discontinuous phrases
• 4. Conclusion

Lorenzo Gregori, Andrea Amelio Ravelli et Alessandro Panunzi

• 1. Introduzione
• 2. Risorse
• 2.1 IMAGACT
• 2.2 BabelNet
• 3. L’esperimento di linking
• 3.1 Il dataset
• 3.2 Gli algoritmi
• 4. Valutazione
• 4.1 Risultati della valutazione
• 4.2 Conclusioni

Raffaele Guarasci et Alessandro Maisto

• 1. Introduction
• 2. Related Work
• 3. Proposed approach
• 3.1 Medical morphemes ontology (MedITA)
• 3.2 MT System
• 4. Experiment and Evaluation
• 5. Conclusions

Giorgio Guzzetta et Federico Nanni

• 1. Introduction
• 2. The problem of literary influence
• 3. Trasferring of memory and language: Raben’s project
• 3.1 A specific case study
• 4. Detecting similarities between two texts
• 4.1 A different approach, pt. 1
• 4.2 A different approach, pt. 2
• 5. Results and conclusion

Tobias Horsmann et Torsten Zesch

• 1. Introduction
• 2. Baseline Tagger
• 3. Domain Adaptation Approaches
• 3.1 More Training Data
• 3.2 More Knowledge
• 4. Combining Approaches
• 5. Practical Issues
• 5.1 Coarse-grained Performance
• 5.2 Influence of the System Architecture
• 6. Conclusion

Mirko Lai, Daniela Virone, Cristina Bosco et al.

• 1. Introduction
• 2. Related work
• 3. Collection and composition of the data set
• 4. Data analysis and data-driven annotation
• 5. Conclusions and future work

Verena Lyding, Michel Généreux, Katalin Szabò et al.

• 1. Introduction
• 2. Related work
• 3. Overview of the OPATCH platform
• 4. Data
• 4.1 Historical newspaper data
• 4.2 ‘Korpus Südtirol’ core corpus
• 5. Platform design
• 5.1 User requirements
• 5.2 Format and annotation requirements
• 5.3 Portal specifications
• 5.4 Back-end specification
• 6. Processing and annotation chain
• 6.1 OCR and post-processing
• 6.2 Layout recognition
• 6.3 Metadata collection
• 6.4 Linguistic annotations: tokenization, lemmatization, part-of-speech and NER
• 6.5 Transformation for retrieval engines
• 7. Conclusion

Alessandro Mazzei

• 1. Introduzione
• 2. Una semplice architettura di NLG
• 3. Teorie della persusione per la generazione del linguaggio
• 4. Conclusioni e sviluppi futuri

Anne-Lyse Minard, Manuela Speranza, Rachele Sprugnoli et al.

• 1. Introduction
• 2. Related Evaluation Tasks
• 3. Task Description
• 3.1 Subtask 1: Factuality Profiling
• 3.2 Subtask 2: Temporal Anchoring
• 4. Dataset Description
• 4.1 Subtask 1: Factuality Profiling
• 4.2 Subtask 2: Temporal Anchoring
• 5. Evaluation
• 5.1 Subtask 1: Factuality Profiling
• 5.2 Subtask 2: Temporal Anchoring
• 6. Discussion and Conclusions

Johanna Monti, Federico Sangati et Mihael Arcan

Towards a methodology for annotating MWEs in parallel multilingual corpora

• 1. Introduction
• 2. Related work
• 3. TED-MWE
• 3.1 The TED Corpus
• 3.2 MWE Annotation Guidelines
• 4. Annotation Process
• 4.1 Statistical Machine Translation
• 5. MWE Annotation Statistics
• 6. Conclusions

Giovanni Moretti, Rachele Sprugnoli et Sara Tonelli

• 1. Introduction
• 2. System Overview
• 3. Evaluation
• 4. Applications
• 5. Conclusions

Malvina Nissim, Sara Castagnoli, Francesca Masini et al.

• 1. Introduction
• 2. Benchmarks
• 3. Experimental evaluation
• 3.1 Data and WoC extraction
• 3.2 Evaluation against a dictionary
• 3.3 Human-based evaluation with experts
• 3.4 Human-based evaluation with laypeople
• 3.4.1 Participation and results
• 3.4.2 Experts vs laypeople
• 4. Discussion and conclusion

Nahli Ouafae et Simone Marchi

• 1. Introduction
• 2. Morphological structure of Arabic words
• 2.1 Maximal and minimal words
• 2.2 Ambiguity in tokenization
• 2.3 Morpho-syntactic characteristics
• 2.4 Verb semantics and agreement
• 3 Word processing issues
• 3.1 Problems and solutions
• Case 1
• Case 2
• 4 Conclusion and future research

Lucia C. Passaro, Laura Pollacci et Alessandro Lenci

• 1. Introduction and related work
• 2. ItEM
• 2.1 Seed collection and annotation
• 2.2 Bootstrapping ItEM
• 2.3 Validation
• 3. Results
• 4. Conclusion

Marco Passarotti, Berta González Saavedra et Christophe Onambélé Manga

• 1. Introduction
• 2. The Lexical Resources
• 2.1 The Latin Valency Lexicon Vallex
• 2.2 The Latin WordNet
• 3. Comparing the Lexical Resources
• 3.1 Method
• 3.2 Selecting the Vallex Subsets
• 3.3 Results and Discussion
• 4. Conclusion and Future Work

Serena Pelosi

• 1. Introduction
• 2. State of the Art
• 3. Prior Polarity: Building and Propagating Italian Lexical Resources
• 4. Contextual Polarity: Rules for the Sentence-level Sentiment Analysis
• 5. Doxa: a Document-level Opinionated teXt Analyzer
• 6. Conclusion

Maria Laura Pierucci

• 1. Introduction
• 2. Storytelling fra passato e presente
• 2.1 Lo storytelling e le sue 'scritture brevi'
• 2.2 Storytelling nell’era digitale: case studies e la funzione delle ‘scritture brevi’
• Conclusioni

Stefan Richter, Andrea Cimino, Felice Dell’Orletta et al.

• 1. Introduction and Background
• 2. Our Approach
• 3. Corpus
• 4. Features
• 5. Experiments and Discussion

Irene Russo et Irene De Felice

• 1. Introduction
• 2. Manual Annotation of Grasping Possibilities
• 3. Semantic and physical knowledge about artifacts: guessing grasping possibilities
• 3.1 Classification Experiment
• 4. Conclusions and Future Works

Manuela Sanguinetti

• 1. Introduction
• 2. Catenae: a brief introduction
• 3. Catenae extraction and alignment
• 4. Using catenae in PBSMT
• 4.1 Data
• 4.2 Experimental setup
• 4.3 Results
• 5. Conclusions

Manuela Speranza et Anne-Lyse Minard

• 1. Introduction
• Related work
• 3. Annotation available in the English source corpus
• 3.1 Annotation at document level
• 3.2 Annotation at corpus level
• 4. Italian language specific annotations
• 5. Annotation of WItaC
• 6. Dataset Description
• 7. Conclusions and future work

Rachele Sprugnoli, Felice Dell’Orletta, Tommaso Caselli et al.

• 1. Introduction
• 2. Motivation and Background
• 3. Task Description
• 3.1 Annotation and Data Format
• 4. Evaluation and Discussion

Sabrina Stehwien et Sebastian Padó

• 1. Introduction
• 2. Datasets
• 3. Models
• 4. Experiments and Results
• 4.1 Experimental Setup
• 4.2 Main Experimental Results
• 4.3 Topic vs. L1 Transfer at the Feature Level
• 5. Conclusion

Evgeny A. Stepanov et Giuseppe Riccardi

• 1. Introduction
• 2. Discourse Connectives and Their Senses
• 3. Methodology
• 3.1 Data Set
• 3.2 Baseline Results
• 3.3 Representation of Discourse Connectives as Features
• 4. Experiments and Results
• 4.1 Discourse Connectives as Stand-Alone Features
• 4.2 Fusion of Bag-of-Words and Discourse Connective Features
• 4.3 N-grams of Discourse Connective Senses
• 5. Conclusions

Marco Stranisci, Cristina Bosco, Viviana Patti et al.

• 1. Introduction
• 2. Data collection: criteria and subcorpora
• 3. Annotation and disagreement analysis
• 4. Analysis of corpora
• 5. Conclusions

Hamed Zamani, José G. C. de Souza, Matteo Negri et al.

• 1. Introduction
• 2. Methodology
• 3. Experiments
• 5. Conclusions