Publications

@conference{	11568_1116100,

title = {Mining the Stream of News for City Areas Profiling: A Case Study for the City of Rome},

author = {A. Bechini and A. Bondielli and J. L. C. Barcena and P. Ducange and F. Marcelloni and A. Renda},

doi = {10.1109/SMARTCOMP52413.2021.00066},

isbn = {978-1-6654-1252-0},

year  = {2021},

date = {2021-01-01},

booktitle = {Proceedings - 2021 IEEE International Conference on Smart Computing, SMARTCOMP 2021},

pages = {317–322},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1113566,

title = {Leveraging CLIP for Image Emotion Recognition},

author = {Alessandro Bondielli and Lucia C. Passaro},

url = {http://ceur-ws.org/Vol-3015/paper172.pdf},

year  = {2021},

date = {2021-01-01},

booktitle = {Proceedings of the Fifth Workshop on Natural Language for Artificial Intelligence (NL4AI 2021) co-located with 20th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2021)},

volume = {3015},

publisher = {CEUR-WS},

address = {Aachen},

abstract = {Multi-modal neural models that are able to encode and process both visual and textual data are becoming more and more common in the last few years. Such models enable new ways to learn the interaction between vision and text, and thus can be successfully applied to tasks of varying complexity in the domain of image and text classification. However, such models are traditionally oriented to learn grounded properties of images and of the objects they depict and less suited to solve tasks involving subjective characteristics, such as the emotions they can convey in viewers. In this paper, we provide some insights in the performances of the recently released OpenAI CLIP model for an emotion classification task. We evaluate the model both under zero-shot settings and via fine tuning on an image-emotion dataset. We compare the performances of CLIP both in a zero-shot and fine-tuning setting on (i) a standard benchmark dataset for object recognition (ii) an image-emotion dataset. Moreover, we evaluate to which extent a CLIP model adapted to emotions is able to retain general knowledge and generalization capabilities.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1134758,

title = {Language Disparity in the Interaction with Chatbots for the Administrative Domain},

author = {Martina Miliani and Marina Benedetti and Alessandro Lenci},

url = {https://aiucd2021.labcd.unipi.it/wp-content/uploads/2021/05/AIUCD2021_BOA-versione3A.pdf},

isbn = {9788894253559},

year  = {2021},

date = {2021-01-01},

booktitle = {AIUCD 2021 – DHs for society: e-quality, participation, rights and values in the Digital Age},

pages = {545–549},

publisher = {Associazione per l’Informatica Umanistica e la Cultura Digitale},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Croce2021,

title = {GQA-it: Italian question answering on image scene graphs},

author = {D. Croce and L. C. Passaro and A. Lenci and R. Basili},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85121264262&partnerID=40&md5=c093094350b1b591eb55ee9acf3af687},

year  = {2021},

date = {2021-01-01},

journal = {CEUR Workshop Proceedings},

volume = {3033},

abstract = {The recent breakthroughs in the field of deep learning have lead to state-of-the-art results in several Computer Vision and Natural Language Processing tasks such as Visual Question Answering (VQA). Nevertheless, the training requirements in cross-linguistic settings are not completely satisfying at the moment. The datasets suitable for training VQA systems for non-English languages are still not available, thus representing a significant barrier for most neural methods. This paper explores the possibility of acquiring in a semiautomatic fashion a large-scale dataset for VQA in Italian. It consists of more than 1 M question-answer pairs over 80k images, with a test set of 3,000 question-answer pairs manually validated. To the best of our knowledge, the models trained on this dataset represent the first attempt to approach VQA in Italian, with experimental results comparable with those obtained on the English original material. © 2021 for this paper by its author. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1115778,

title = {Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge},

author = {Paolo Pedinotti and Giulia Rambelli and Emmanuele Chersoni and Enrico Santus and Alessandro Lenci and Philippe Blache},

url = {https://aclanthology.org/2021.starsem-1.1},

doi = {10.18653/v1/2021.starsem-1.1},

isbn = {978-1-954085-77-0},

year  = {2021},

date = {2021-01-01},

booktitle = {Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics},

pages = {1–11},

publisher = {Association for Computational Linguistics},

abstract = {Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate. While much work has been devoted to modeling the typicality relation between verbs and arguments in isolation, in this paper we take a broader perspective by assessing whether and to what extent computational approaches have access to the information about the typicality of entire events and situations described in language (Generalized Event Knowledge). Given the recent success of Transformers Language Models (TLMs), we decided to test them on a benchmark for the dynamic estimation of thematic fit. The evaluation of these models was performed in comparison with SDM, a framework specifically designed to integrate events in sentence meaning representations, and we conducted a detailed error analysis to investigate which factors affect their behavior. Our results show that TLMs can reach performances that are comparable to those achieved by SDM. However, additional analysis consistently suggests that TLMs do not capture important aspects of event knowledge, and their predictions often depend on surface linguistic features, such as frequent words, collocations and syntactic patterns, thereby showing sub-optimal generalization abilities.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1134756,

title = {Chi ha paura delle Digital Humanities? Miti e realtà del rapporto tra computer, testo e lingua},

author = {Alessandro Lenci},

isbn = {978-88-907905-7-7},

year  = {2021},

date = {2021-01-01},

booktitle = {Letteratura e Scienze Atti delle sessioni parallele del XXIII Congresso dell’ADI (Associazione degli Italianisti)},

pages = {1–7},

publisher = {Adi editore},

address = {Roma},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1134766,

title = {A howling success or a working sea? Testing what BERT knows about metaphors},

author = {Paolo Pedinotti and Eliana Di Palma and Ludovica Cerini and Alessandro Lenci},

url = {https://aclanthology.org/2021.blackboxnlp-1.13.pdf},

isbn = {978-1-955917-06-3},

year  = {2021},

date = {2021-01-01},

booktitle = {Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP},

pages = {192–204},

publisher = {Association for Computational Linguistics},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{miliani-etal-2020-fraque,

title = {FRAQUE: a FRAme-based QUEstion-answering system for the Public Administration domain},

author = {Martina Miliani and Lucia C. Passaro and Alessandro Lenci},

editor = {Doaa Samy and David Pérez-Fernández and Jerónimo Arenas-García},

url = {https://aclanthology.org/2020.lt4gov-1.2/},

isbn = {979-10-95546-62-7},

year  = {2020},

date = {2020-05-01},

booktitle = {Proceedings of the 1st Workshop on Language Technologies for Government and Public Administration (LT4Gov)},

pages = {7–14},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {In this paper, we propose FRAQUE, a question answering system for factoid questions in the Public administration domain. The system is based on semantic frames, here intended as collections of slots typed with their possible values. FRAQUE queries unstructured textual data and exploits the potential of different approaches: it extracts pattern elements from texts which are linguistically analyzed through statistical methods.FRAQUE allows Italian users to query vast document repositories related to the domain of Public Administration. Given the statistical nature of most of its components such as word embeddings, the system allows for a flexible domain and language adaptation process. FRAQUE's goal is to associate questions with frames stored into a Knowledge Graph along with relevant document passages, which are returned as the answer.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{boschetti-etal-2020-voices,

title = {``Voices of the Great War'': A Richly Annotated Corpus of Italian Texts on the First World War},

author = {Federico Boschetti and Irene De Felice and Stefano Dei Rossi and Felice Dell'Orletta and Michele Di Giorgio and Martina Miliani and Lucia C. Passaro and Angelica Puddu and Giulia Venturi and Nicola Labanca and Alessandro Lenci and Simonetta Montemagni},

editor = {Nicoletta Calzolari and Frédéric Béchet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis},

url = {https://aclanthology.org/2020.lrec-1.114/},

isbn = {979-10-95546-34-4},

year  = {2020},

date = {2020-05-01},

urldate = {2020-05-01},

booktitle = {Proceedings of the Twelfth Language Resources and Evaluation Conference},

pages = {911–918},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {``Voices of the Great War'' is the first large corpus of Italian historical texts dating back to the period of First World War. This corpus differs from other existing resources in several respects. First, from the linguistic point of view it gives account of the wide range of varieties in which Italian was articulated in that period, namely from a diastratic (educated vs. uneducated writers), diaphasic (low/informal vs. high/formal registers) and diatopic (regional varieties, dialects) points of view. From the historical perspective, through a collection of texts belonging to different genres it represents different views on the war and the various styles of narrating war events and experiences. The final corpus is balanced along various dimensions, corresponding to the textual genre, the language variety used, the author type and the typology of conveyed contents. The corpus is fully annotated with lemmas, part-of-speech, terminology, and named entities. Significant corpus samples representative of the different ``voices'' have also been enriched with meta-linguistic and syntactic information. The layer of syntactic annotation forms the first nucleus of an Italian historical treebank complying with the Universal Dependencies standard. The paper illustrates the final resource, the methodology and tools used to build it, and the Web Interface for navigating it.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1070127,

title = {Voices of the great war: A richly annotated corpus of Italian texts on the first world war},

author = {Alessandro Lenci and Simonetta Montemagni and Federico Boschetti and Irene De Felice and Stefano Dei Rossi and Felice Dell’Orletta and Michele Di Giorgio and Martina Miliani and Lucia Passaro and Angelica Puddu and Giulia Venturi and Nicola Labanca},

url = {https://www.aclweb.org/anthology/2020.lrec-1.114.pdf},

isbn = {979-10-95546-34-4},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the 12th Language Resources and Evaluation Conference (LREC)},

pages = {911–918},

publisher = {ELRA},

address = {Paris},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Passaro2020,

title = {UNIPI-NLE at CheckThat! 2020: Approaching Fact Checking from a Sentence Similarity Perspective through the Lens of Transformers},

author = {L. C. Passaro and A. Bondielli and A. Lenci and F. Marcelloni},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85121823898&partnerID=40&md5=dd0ee8e9f0b443e15124a6a2d8156ab3},

year  = {2020},

date = {2020-01-01},

journal = {CEUR Workshop Proceedings},

volume = {2696},

abstract = {This paper describes a Fact Checking system based on a combination of Information Extraction and Deep Learning strategies to approach the task named “Verified Claim Retrieval” (Task 2) for the CheckThat! 2020 evaluation campaign. The system is based on two main assumptions: a claim that verifies a tweet is expected i) to mention the same entities and keyphrases, and ii) to have a similar meaning. The former assumption has been addressed by exploiting an Information Extraction module capable of determining the pairs in which the tweet and the claim share at least a named entity or a relevant keyword. To address the latter, we exploited Deep Learning to refine the computation of the text similarity between a tweet and a claim, and to actually classify the pairs as correct matches or not. In particular, the system has been built starting from a pre-trained Sentence-BERT model, on which two cascade fine-tuning steps have been applied in order to i) assign a higher cosine similarity to gold pairs, and ii) classify a pair as correct or not. The final ranking produced by the system is the probability of the pair labelled as correct. Overall, the system reached a 0.91 MAP@5 on the test set. Copyright © 2020 for this paper by its authors.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1067421,

title = {UNIPI-NLE at CheckThat! 2020: Approaching Fact Checking from a Sentence Similarity Perspective Through the Lens of Transformers},

author = {Lucia Passaro and Alessandro Bondielli and Alessandro Lenci and Francesco Marcelloni},

url = {http://ceur-ws.org/Vol-2696/paper_169.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {Working Notes of CLEF 2020 - Conference and Labs of the Evaluation Forum},

volume = {2696},

publisher = {CEUR},

abstract = {This paper describes a Fact Checking system based on a combination of Information Extraction and Deep Learning strategies to approach the task named Verified Claim Retrieval" (Task 2) for the CheckThat! 2020 evaluation campaign. The system is based on two main assumptions: a claim that verifies a tweet is expected i) to mention the same entities and keyphrases, and ii) to have a similar meaning. The former assumption has been addressed by exploiting an Information Extraction module capable of determining the pairs in which the tweet and the claim share at least a named entity or a relevant keyword. To address the latter, we exploited Deep Learning to refine the computation of the text similarity between a tweet and a claim, and to actually classify the pairs as correct matches or not. In particular, the system has been built starting from a pre-trained Sentence-BERT model, on which two cascade fine-tuning steps have been applied in order to i) assign a higher cosine similarity to gold pairs, and ii) classify a pair as correct or not. The final ranking produced by the system is the probability of the pair labelled as correct. Overall, the system reached a 0.91 MAP@5 on the test set.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1070102,

title = {Representing Verbs with Visual Argument Vectors},

author = {Irene Sucameli and Alessandro Lenci},

url = {https://www.aclweb.org/anthology/2020.lrec-1.718.pdf},

isbn = {979-10-95546-34-4},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the 12th Language Resources and Evaluation Conference (LREC)},

pages = {5865–5870},

publisher = {ELRA},

address = {Paris},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Basile2020,

title = {Preface to the EVALITA 2020 proceedings},

author = {V. Basile and D. Croce and M. Di Maro and L. C. Passaro},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85097536726&partnerID=40&md5=12e2766d877482fff2be24e0cc848144},

year  = {2020},

date = {2020-01-01},

journal = {CEUR Workshop Proceedings},

volume = {2765},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1069939,

title = {PISA: A measure of Preference In Selection of Arguments to model verb argument recoverability},

author = {Giulia Cappelli and Alessandro Lenci},

url = {https://www.aclweb.org/anthology/2020.starsem-1.14.pdf},

isbn = {978-1-952148-32-3},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics},

pages = {131–136},

publisher = {Association for Computational Linguistics},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1069972,

title = {Less is MORE: a MultimOdal system for tag REfinement},

author = {Lucia Passaro and Alessandro Lenci},

url = {http://ceur-ws.org/Vol-2735/paper32.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the 4th Workshop on Natural Language for Artificial Intelligence (NL4AI 2020)},

volume = {2735},

pages = {44–58},

publisher = {CEUR},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Passaro202044,

title = {Less is MORE: A multimOdal system for tag REfinement},

author = {L. C. Passaro and A. Lenci},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099023375&partnerID=40&md5=3843481376fa7f8019013f192af72e93},

year  = {2020},

date = {2020-01-01},

journal = {CEUR Workshop Proceedings},

volume = {2735},

pages = {44-58},

abstract = {With the proliferation of image-based social media, an extremely large amount of multimodal data is being produced. Very often image contents are published together with a set of user defined metadata such as tags and textual descriptions. Despite being very useful to enhance traditional image retrieval, user defined tags on social media have been proven to be noneffective to index images because they are inuenced by personal experiences of the owners as well as their will of promoting the published contents. To be analyzed and indexed, multimodal data require algorithms able to jointly deal with textual and visual data. This research presents a multimodal approach to the problem of tag refinement, which consists in separating the relevant descriptors (tags) of images from noisy ones. The proposed method exploits both Natural Language Processing (NLP) and Computer Vision (CV) techniques based on deep learning to find a match between the textual information and visual content of social media posts. Textual semantic features are represented with (multilingual) word embeddings, while visual ones are obtained with image classification. The proposed system is evaluated on a manually annotated Italian dataset extracted from Instagram achieving 68% of weighted F1-score. Copyright © 2020 for this paper by its authors.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1074629,

title = {FRAQUE: a FRAme-based QUEstion-answering system for the Public Administration domain},

author = {Martina Miliani and Lucia Passaro and Alessandro Lenci},

url = {https://www.aclweb.org/anthology/2020.lt4gov-1.2/},

isbn = {979-10-95546-62-7},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the First workshop on Language Technologies for Government and Public Admnistration (LT4Gov)},

pages = {7–14},

publisher = {ELRA},

address = {Paris},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1055590,

title = {Exploiting Categorization of Online News for Profiling City Areas},

author = {A. Bondielli and P. Ducange and F. Marcelloni},

doi = {10.1109/EAIS48028.2020.9122777},

isbn = {978-1-7281-4384-2},

year  = {2020},

date = {2020-01-01},

booktitle = {IEEE Conference on Evolving and Adaptive Intelligent Systems},

volume = {2020-},

pages = {1–8},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1112544,

title = {EVALITA 2020: Overview of the 7th evaluation campaign of natural language processing and speech tools for Italian},

author = {V. Basile and M. Di Maro and D. Croce and L. Passaro},

url = {http://ceur-ws.org/Vol-2765/overview.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {EVALITA 2020: Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian},

volume = {2765},

publisher = {CEUR-WS},

abstract = {The Evaluation Campaign of Natural Language Processing and Speech Tools for Italian (EVALITA) is the biennial initiative aimed at promoting the development of language and speech technologies for the Italian language. EVALITA is promoted by the Italian Association of Computational Linguistics (AILC) and it is endorsed by the Italian Association for Artificial Intelligence (AIxIA) and the Italian Association for Speech Sciences (AISV). 

EVALITA provides a shared framework where different systems and approaches can be scientifically evaluated and compared with each other with respect to a large variety of tasks, suggested and organized by the Italian research community. The proposed tasks represent scientific challenges where methods, resources, and systems can be tested against shared benchmarks representing linguistic open issues or real world applications, possibly in a multilingual and/or multi-modal perspective. The collected data 

sets provide big opportunities for scientists to explore old and new problems concerning NLP in Italian as well as to develop solutions and to discuss the NLP-related issues within the community. Some tasks are traditionally present in the evaluation campaign, while others are completely new. 

This paper introduces the tasks proposed at EVALITA 2020 and provides an overview to the participants and systems whose descriptions and obtained results are reported in these Proceedings.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1327957,

title = {EVALITA 2020: Overview of the 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian},

author = {Valerio Basile and Danilo Croce and Maria Di Maro and Lucia C. Passaro},

url = {https://books.openedition.org/aaccademia/6747?lang=en},

doi = {10.4000/books.aaccademia.6732},

isbn = {9791280136329},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian Final Workshop},

pages = {5–11},

publisher = {Lexis Compagnia Editoriale in Torino srl},

address = {Torino},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1069937,

title = {Don’t Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations},

author = {Paolo Pedinotti and Alessandro Lenci},

url = {https://www.aclweb.org/anthology/2020.coling-main.602.pdf},

isbn = {978-1-952148-27-9},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},

pages = {6831–6837},

address = {Barcelona, Spain},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{miliani2020dankmemes,

title = {Dankmemes@ evalita 2020: The memeing of life: Memes, multimodality and politics},

author = {Martina Miliani and Giulia Giorgi and Ilir Rama and Guido Anselmi and Gianluca E Lebani and others},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian Final Workshop (EVALITA 2020)},

organization = {Accademia University Press},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1069933,

title = {Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation},

author = {Giulia Rambelli and Emmanuele Chersoni and Alessandro Lenci and Phlippe Blache and Chu-Ren Huang},

url = {https://www.aclweb.org/anthology/2020.aacl-main.26/},

isbn = {978-1-952148-91-0},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing},

pages = {224–234},

publisher = {Association for Computational Linguistics},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1069968,

title = {CAPISCO@CONcreTEXT 2020: (Un)supervised Systems to Contextualize Concreteness with Norming Data},

author = {Alessandro Bondielli and Gianluca E. Lebani and Lucia Passaro and Alessandro Lenci},

url = {http://ceur-ws.org/Vol-2765/paper123.pdf},

isbn = {9791280136275},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian Final Workshop (EVALITA 2020)},

volume = {2765},

pages = {327–333},

publisher = {Accademia University Press},

address = {Torino, Italy},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Bondielli2020,

title = {CAPISCO @ CONcreTEXT 2020: (Un)supervised systems to contextualize concreteness with norming data},

author = {A. Bondielli and G. E. Lebani and L. C. Passaro and A. Lenci},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85097543971&partnerID=40&md5=92d1275a1d1d93b4de74fcbee6e8cc40},

year  = {2020},

date = {2020-01-01},

journal = {CEUR Workshop Proceedings},

volume = {2765},

abstract = {This paper describes several approaches to the automatic rating of the concreteness of concepts in context, to approach the EVALITA 2020 “CONcreTEXT” task. Our systems focus on the interplay between words and their surrounding context by (i) exploiting annotated resources, (ii) using BERT masking to find potential substitutes of the target in specific contexts and measuring their average similarity with concrete and abstract centroids, and (iii) automatically generating labelled datasets to fine tune transformer models for regression. All the approaches have been tested both on English and Italian data. Both the best systems for each language ranked second in the task. Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1070006,

title = {Becoming JILDA},

author = {Irene Sucameli and Alessandro Lenci and Bernardo Magnini and Maria Simi and Manuela Speranza},

isbn = {979-12-80136-28-2},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the Seventh Italian Conference on Computational Linguistics (CLiC-it 2020)},

pages = {409–414},

publisher = {Accademia University Press},

address = {Torino, Italy},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1070086,

title = {Are Word Embeddings Really a Bad Fit for the Estimation of Thematic Fit?},

author = {Emmanuele Chersoni and Ludovica Pannitto and Enrico Santus and Alessandro Lenci and Chu-Ren Huang},

url = {https://www.aclweb.org/anthology/2020.lrec-1.700.pdf},

isbn = {979-10-95546-34-4},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the 12th Language Resources and Evaluation Conference (LREC)},

pages = {5708–5713},

publisher = {ELRA},

address = {Paris},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1031587,

title = {What Do Neural Networks Actually Learn, When They Learn to Identify Idioms?},

author = {MARCO SILVIO GIUSEPPE Senaldi and Yuri Bizzoni and Alessandro Lenci},

doi = {10.7275/x015-az15},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the Society for Computation in Linguistics},

pages = {310–313},

address = {New York},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Miliani2019,

title = {Text frame detector: Slot filling based on domain knowledge bases},

author = {M. Miliani and L. C. Passaro and A. Lenci},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85074851799&partnerID=40&md5=0e157a6185635fdd84fdd87617f4e77d},

year  = {2019},

date = {2019-01-01},

journal = {CEUR Workshop Proceedings},

volume = {2481},

abstract = {In this paper we present a system called Text Frame Detector (TFD) which aims at populating a frame-based ontology in a graph-based structure. Our system organizes textual information into frames, according to a predefined set of semantically informed patterns linking pre-coded information such as named entities, simple and complex terms. Given the semiautomatic expansion of such information with word embeddings, the system can be easily adapted to new domains. Copyright © 2019 for this paper by its authors.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1032639,

title = {Text Frame Detector: Slot Filling Based On Domain Knowledge Bases},

author = {Martina Miliani and Lucia Passaro and Alessandro Lenci},

url = {http://ceur-ws.org/Vol-2481/paper50.pdf},

isbn = {9791280136008},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the Sixth Italian Conference on Computational Linguistics (CLiC-it 2019)},

volume = {2481},

publisher = {Ceur Workshop Proeedings},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1031583,

title = {Multimodal Event Knowledge in Online Sentence Comprehension: The Influence of Visual Context on Anticipatory Eye Movements},

author = {Valentina Benedettini and Pier Marco Bertinetto and Alessandro Lenci and Ken Mcrae},

isbn = {9781510891555},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the 41st Annual Meeting of the Cognitive Science Society (CogSci 2019)},

pages = {1395–1401},

address = {Montreal},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1031585,

title = {Do Idioms Have a Heart? The SIDE (Sentiment of IDiomatic Expressions) Project},

author = {Lucia Passaro and Marco Senaldi and Alessandro Lenci},

doi = {10.7939/r3-vkwf-dr08},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the 11th International Conference on the Mental Lexicon},

pages = {1–4},

address = {Edmonton},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_991550,

title = {Distributional Semantics Meets Construction Grammar. Towards a Unified Usage-Based Model of Grammar and Meaning},

author = {Giulia Rambelli and Emmanuele Chersoni and Philippe Blache and Chu-Ren Huang and Alessandro Lenci},

url = {https://www.aclweb.org/anthology/W19-3312.pdf},

doi = {10.18653/v1/W19-3312},

isbn = {978-1-950737-45-1},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the First International Workshop on Designing Meaning Representations (DMR 2019)},

pages = {110–120},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_1333762,

title = {SemplicePA SEMantic instruments for PubLIc administrators and CitizEns},

author = {M. Miliani and A. Gabbolini and L. C. Passaro and F. Sandrelli and A. Lenci and R. Battistelli},

url = {https://www.garr.it/it/news-e-eventi/pubblicazioni/atti-delle-conferenze/atti-della-conferenza-garr-2017},

doi = {10.978.88905077/79},

isbn = {9788890507779},

year  = {2018},

date = {2018-01-01},

booktitle = {Conferenza GARR 2017 - The data way to Science},

pages = {158–163},

publisher = {Ass. Consortium GARR},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11568_953548,

title = {SemEval-2018 Task 10: Capturing Discriminative Attributes},

author = {Alicia Krebs and Alessandro Lenci and Denis Paperno},

isbn = {978-1-948087-20-9},

year  = {2018},

date = {2018-01-01},

booktitle = {The International Workshop on Semantic Evaluation: Proceedings of the Twelfth Workshop},

pages = {732–740},

publisher = {Association for Computational Linguistics},

address = {Stroudsburg},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}