-
Pas de résultats
- Navigation
Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020
Preface
Organising Committee
Fine-grained sentiment analysis: a piece of cake?
Interaction-aware multimodal dialogue with conversational agents
Distributional Semantics: Yesterday, Today, and Tomorrow
Quantitative Linguistic Investigations across Universal Dependencies Treebanks
A Machine Learning approach for Sentiment Analysis for Italian Reviews in Healthcare
Investigating Proactivity in Task-Oriented Dialogues
A Diachronic Italian Corpus based on “L’Unità”
Domain Adaptation for Text Classification with Weird Embeddings
Personal-ITY: A Novel YouTube-based Corpus for Personality Prediction in Italian
The “Corpus Anchise 320” and the analysis of conversations between healthcare workers and people with dementia
Gender Bias in Italian Word Embeddings
Automatic Induction of FrameNet Lexical Units in Italian
Detecting Early Onset of Depression from Social Media Text using Learned Confidence Scores
Building a Treebank in Universal Dependencies for Italian Sign Language
Analysis of lexical semantic changes in corpora with the Diachronic Engine
Hate Speech Detection with Machine-Translated Data: The Role of Annotation Scheme, Class Imbalance and Undersampling
UDante: First Steps Towards the Universal Dependencies Treebank of Dante’s Latin Works
“Spotto la quarantena": per una analisi dell’italiano scritto degli studenti universitari via social network in tempo di COVID-19
Italian Counter Narrative Generation to Fight Online Hate Speech
Surviving the Legal Jungle: Text Classification of Italian Laws in extremely Noisy conditions
Clustering verbal Objects: manual and automatic procedures compared
GePpeTto Carves Italian into a Language Model
Phonological Layers of Meaning: A Computational Exploration of Sound Iconicity
Natural Language Generation in Dialogue Systems for Customer Care
Cross-Language Transformer Adaptation for Frequently Asked Questions
How good are humans at Native Language Identification? A case study on Italian L2 writings
You Don’t Say… Linguistic Features in Sarcasm Detection
Risorse linguistiche di varietà storiche di italiano: il progetto TrAVaSI1
AriEmozione: Identifying Emotions in Opera Verses
The AEREST Reading Database
Græcissāre: Ancient Greek Loanwords in the LiLa Knowledge Base of Linguistic Resources for Latin
L’impatto emotivo della comunicazione istituzionale durante la pandemia di Covid-19: uno studio di Twitter Sentiment Analysis
On Knowledge Distillation for Direct Speech Translation
Predicting Social Exclusion: A Study of Linguistic Ostracism in Social Networks
Grounded and Ungrounded Referring Expressions in Human Dialogues: Language Mirrors Different Grounding Conditions
Predicting movie-elicited emotions from dialogue in screenplay text: A study on “Forrest Gump”
Point Break: Surfing Heterogeneous Data for Subtitle Segmentation
How granularity of orthography-phonology mappings affect reading development: Evidence from a computational model of English word reading and spelling
Simple Data Augmentation for Multilingual NLU in Task Oriented Dialogue Systems
The E3C Project: Collection and Annotation of a Multilingual Corpus of Clinical Cases1
Monitoring Social Media to Identify Environmental Crimes through NLP A Preliminary Study
Does finger-tracking point to child reading strategies?
Multiword expressions we live by: a validated usage-based dataset from corpora of written Italian
The Style of a Successful Story: a Computational Study on the Fanfiction Genre
A Multimodal Dataset of Images and Text to Study Abusive Language
A Resource for Detecting Misspellings and Denoising Medical Text Data
Is Neural Language Model Perplexity Related to Readability?
Italian Transformers Under the Linguistic Lens
BERTino: an Italian DistilBERT model
ItaGLAM: A corpus of Cultural Communication on Twitter during the Pandemic
Creativity Embedding: a vector to characterise and classify plausible triples in deep learning NLP models
The CREENDER Tool for Creating Multimodal Datasets of Images and Comments
(Stem and Word) Predictability in Italian verb paradigms: An Entropy-Based Study Exploiting the New Resource LeFFI
A deep learning model for the analysis of medical reports in ICD-10 clinical coding task
Exploring Attention in a Multimodal Corpus of Guided Tours
A Case Study of Natural Gender Phenomena in Translation. A Comparison of Google Translate, Bing Microsoft Translator and DeepL for English to Italian, French and Spanish
Multifunctional ISO standard Dialogue Act tagging in Italian
Tracing Metonymic Relations in T-PAS: An Annotation Exercise on a Corpus-based Resource for Italian
Datasets and Models for Authorship Attribution on Italian Personal Writings
The Archaeo-Term Project: Multilingual Terminology in Archaeology
Exploiting Distributional Semantics Models for Natural Language Context-aware Justifications for Recommender Systems
MultiEmotions-It: a New Dataset for Opinion Polarity and Emotion Analysis for Italian
Becoming JILDA
How “BERTology" Changed the State-of-the-Art also for Italian NLP
Valutazione umana di DeepL a livello di frase per le traduzioni di testi specialistici dall’inglese verso l’italiano
Overprotective Training Environments Fall Short at Testing Time: Let Models Contribute to Their Own Training
Topic Modelling Games
Dialog-based Help Desk through Automated Question Answering and Intent Detection
#andràtuttobene: Images, Texts, Emojis and Geodata in a Sentiment Analysis Pipeline
Polarity Imbalance in Lexicon-based Sentiment Analysis
Suoidne-varra-bleahkka-mála-bihkka-senet-dielku ‘hay-blood-ink-paint-tar-mustard-stain’ – Should compounds be lexicalized in NLP?
Analyses of Character Emotions in Dramatic Works by Using EmoLex Unigrams
- Table des matières Johanna Monti, Felice Dell’Orletta et Fabio Tamburini
Preface
Keynote Talks and Tutorial
Veronique HosteFine-grained sentiment analysis: a piece of cake?
Alessandro LenciDistributional Semantics: Yesterday, Today, and Tomorrow
Contributed Papers
Chiara Alzetta, Felice Dell’Orletta, Simonetta Montemagni et al.Quantitative Linguistic Investigations across Universal Dependencies Treebanks
Luca Bacco, Andrea Cimino, Luca Paulon et al.A Machine Learning approach for Sentiment Analysis for Italian Reviews in Healthcare
Vevake Balaraman et Bernardo MagniniInvestigating Proactivity in Task-Oriented Dialogues
Pierpaolo Basile, Annalina Caputo, Tommaso Caselli et al.A Diachronic Italian Corpus based on “L’Unità”
Elisa Bassignana, Malvina Nissim et Viviana PattiPersonal-ITY: A Novel YouTube-based Corpus for Personality Prediction in Italian
Nicola Benvenuti, Andrea Bolioli, Alessio Bosca et al.The “Corpus Anchise 320” and the analysis of conversations between healthcare workers and people with dementia
Davide Biasion, Alessandro Fabris, Gianmaria Silvello et al.Gender Bias in Italian Word Embeddings
Silvia Brambilla, Danilo Croce, Fabio Tamburini et al.Automatic Induction of FrameNet Lexical Units in Italian
Ana-Maria Bucur et Liviu P. DinuDetecting Early Onset of Depression from Social Media Text using Learned Confidence Scores
Gaia Caligiore, Cristina Bosco et Alessandro MazzeiBuilding a Treebank in Universal Dependencies for Italian Sign Language
Pierluigi Cassotti, Pierpaolo Basile, Marco De Gemmis et al.Analysis of lexical semantic changes in corpora with the Diachronic Engine
Camilla Casula et Sara TonelliHate Speech Detection with Machine-Translated Data: The Role of Annotation Scheme, Class Imbalance and Undersampling
Flavio M. Cecchini, Rachele Sprugnoli, Giovanni Moretti et al.UDante: First Steps Towards the Universal Dependencies Treebank of Dante’s Latin Works
Francesca Chiusaroli, Johanna Monti, Maria Laura Pierucci et al.“Spotto la quarantena": per una analisi dell’italiano scritto degli studenti universitari via social network in tempo di COVID-19
Yi-Ling Chung, Serra Sinem Tekiroğlu et Marco GueriniItalian Counter Narrative Generation to Fight Online Hate Speech
Riccardo Coltrinari, Alessandro Antinori et Fabio CelliSurviving the Legal Jungle: Text Classification of Italian Laws in extremely Noisy conditions
Ilaria Colucci, Elisabetta Jezek et Vít BaisaClustering verbal Objects: manual and automatic procedures compared
Lorenzo De Mattei, Michele Cafagna, Felice Dell’Orletta et al.GePpeTto Carves Italian into a Language Model
Andrea Gregor de Varda et Carlo StrapparavaPhonological Layers of Meaning: A Computational Exploration of Sound Iconicity
Mirko Di Lascio, Manuela Sanguinetti, Luca Anselma et al.Natural Language Generation in Dialogue Systems for Customer Care
Luca Di Liello, Daniele Bonadiman, Cristina Giannone et al.Cross-Language Transformer Adaptation for Frequently Asked Questions
Elisa Di Nuovo, Elisa Corino et Cristina BoscoHow good are humans at Native Language Identification? A case study on Italian L2 writings
Martina Ducret, Lauren Kruse, Carlos Martinez et al.You Don’t Say… Linguistic Features in Sarcasm Detection
Manuel Favaro, Marco Biffi et Simonetta MontemagniRisorse linguistiche di varietà storiche di italiano: il progetto TrAVaSI
Francesco Fernicola, Shibingfeng Zhang, Federico Garcea et al.AriEmozione: Identifying Emotions in Opera Verses
Marcello Ferro, Sara Giulivi et Claudia CappaThe AEREST Reading Database
Greta Franzini, Marco Passarotti, Francesco Mambrini et al.Græcissāre: Ancient Greek Loanwords in the LiLa Knowledge Base of Linguistic Resources for Latin
Gloria Gagliardi, Lorenzo Gregori et Alice SuozziL’impatto emotivo della comunicazione istituzionale durante la pandemia di Covid-19: uno studio di Twitter Sentiment Analysis
Marco Gaido, Mattia Antonino Di Gangi, Matteo Negri et al.On Knowledge Distillation for Direct Speech Translation
Greta Gandolfi et Carlo StrapparavaPredicting Social Exclusion: A Study of Linguistic Ostracism in Social Networks
Eleonora Gualdoni, Raffaella Bernardi, Raquel Fernández et al.Grounded and Ungrounded Referring Expressions in Human Dialogues: Language Mirrors Different Grounding Conditions
Benedetta Iavarone et Felice Dell’OrlettaPredicting movie-elicited emotions from dialogue in screenplay text: A study on “Forrest Gump”
Alina Karakanta, Matteo Negri et Marco TurchiPoint Break: Surfing Heterogeneous Data for Subtitle Segmentation
Alfred Lim, Beth A. O’Brien et Luca OnnisHow granularity of orthography-phonology mappings affect reading development: Evidence from a computational model of English word reading and spelling
Samuel Louvan et Bernardo MagniniSimple Data Augmentation for Multilingual NLU in Task Oriented Dialogue Systems
Bernardo Magnini, Begoña Altuna, Alberto Lavelli et al.The E3C Project: Collection and Annotation of a Multilingual Corpus of Clinical Cases
Raffaele Manna, Antonio Pascucci, Wanda Punzi Zarino et al.Monitoring Social Media to Identify Environmental Crimes through NLP A Preliminary Study
Claudia Marzi, Anna Rodella, Andrea Nadalini et al.Does finger-tracking point to child reading strategies?
Francesca Masini, M. Silvia Micheli, Andrea Zaninello et al.Multiword expressions we live by: a validated usage-based dataset from corpora of written Italian
Andrea Mattei, Dominique Brunato et Felice Dell’OrlettaThe Style of a Successful Story: a Computational Study on the Fanfiction Genre
Stefano Menini, Alessio Palmero Aprosio et Sara TonelliA Multimodal Dataset of Images and Text to Study Abusive Language
Enrico Mensa, Gian Manuel Marino, Davide Colla et al.A Resource for Detecting Misspellings and Denoising Medical Text Data
Alessio Miaschi, Chiara Alzetta, Dominique Brunato et al.Is Neural Language Model Perplexity Related to Readability?
Alessio Miaschi, Gabriele Sarti, Dominique Brunato et al.Italian Transformers Under the Linguistic Lens
Matteo Muffo et Enrico BertinoBERTino: an Italian DistilBERT model
Gennaro Nolano, Carola Carlino, Maria Pia di Buono et al.ItaGLAM: A corpus of Cultural Communication on Twitter during the Pandemic
Isabeau Oliveri, Luca Ardito, Giuseppe Rizzo et al.Creativity Embedding: a vector to characterise and classify plausible triples in deep learning NLP models
Alessio Palmero Aprosio, Stefano Menini et Sara TonelliThe CREENDER Tool for Creating Multimodal Datasets of Images and Comments
Matteo Pellegrini et Alessandra Teresa Cignarella(Stem and Word) Predictability in Italian verb paradigms: An Entropy-Based Study Exploiting the New Resource LeFFI
Marco Polignano, Pierpaolo Basile, Marco De Gemmis et al.A deep learning model for the analysis of medical reports in ICD-10 clinical coding task
Andrea Amelio Ravelli, Antonio Origlia et Felice Dell’OrlettaExploring Attention in a Multimodal Corpus of Guided Tours
Argentina Anna Rescigno, Eva Vanmassenhove, Johanna Monti et al.A Case Study of Natural Gender Phenomena in Translation. A Comparison of Google Translate, Bing Microsoft Translator and DeepL for English to Italian, French and Spanish
Gabriel Roccabruna, Alessandra Cervone et Giuseppe RiccardiMultifunctional ISO standard Dialogue Act tagging in Italian
Emma Romani et Elisabetta JezekTracing Metonymic Relations in T-PAS: An Annotation Exercise on a Corpus-based Resource for Italian
Gaetana Ruggiero, Albert Gatt et Malvina NissimDatasets and Models for Authorship Attribution on Italian Personal Writings
Giulia Speranza, Raffaele Manna, Maria Pia di Buono et al.The Archaeo-Term Project: Multilingual Terminology in Archaeology
Giuseppe Spillo, Cataldo Musto, Marco de Gemmis et al.Exploiting Distributional Semantics Models for Natural Language Context-aware Justifications for Recommender Systems
Rachele SprugnoliMultiEmotions-It: a New Dataset for Opinion Polarity and Emotion Analysis for Italian
Irene Sucameli, Alessandro Lenci, Bernardo Magnini et al.Becoming JILDA
Alberto Testoni et Raffaella BernardiOverprotective Training Environments Fall Short at Testing Time: Let Models Contribute to Their Own Training
Rocco TripodiTopic Modelling Games
Antonio Uva, Pierluigi Roberti et Alessandro MoschittiDialog-based Help Desk through Automated Question Answering and Intent Detection
Pierluigi Vitale, Serena Pelosi et Mariacristina Falco#andràtuttobene: Images, Texts, Emojis and Geodata in a Sentiment Analysis Pipeline
Marco Vassallo, Giuliano Gabrieli, Valerio Basile et al.Polarity Imbalance in Lexicon-based Sentiment Analysis
Linda Wiechetek, Chiara Argese, Tommi A. Pirinen et al.Suoidne-varra-bleahkka-mála-bihkka-senet-dielku ‘hay-blood-ink-paint-tar-mustard-stain’ – Should compounds be lexicalized in NLP?
- imprimer
- Citer
Référence électronique du chapitre
LENCI, Alessandro. Distributional Semantics: Yesterday, Today, and Tomorrow In : Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020 : Bologna, Italy, March 1-3, 2021 [en ligne]. Torino : Accademia University Press, 2020 (généré le 29 mars 2024). Disponible sur Internet : <https://books.openedition.org/aaccademia/9030>. ISBN : 979-12-80136-33-6. DOI : https://doi.org/10.4000/books.aaccademia.9030.Lenci, A. 2020. Distributional Semantics: Yesterday, Today, and Tomorrow. In Dell'Orletta, F., Monti, J., & Tamburini, F. (Eds.), Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020 : Bologna, Italy, March 1-3, 2021. Torino : Accademia University Press. doi :10.4000/books.aaccademia.9030Lenci, Alessandro. “Distributional Semantics: Yesterday, Today, and Tomorrow”. Dell'Orletta, Felice, et al.. Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020 : Bologna, Italy, March 1-3, 2021. Torino : Accademia University Press, 2020. (p. 6) Web. <https://books.openedition.org/aaccademia/9030>.Référence électronique du livre
DELL'ORLETTA, Felice (dir.) ; MONTI, Johanna (dir.) ; et TAMBURINI, Fabio (dir.). Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020 : Bologna, Italy, March 1-3, 2021. Nouvelle édition [en ligne]. Torino : Accademia University Press, 2020 (généré le 29 mars 2024). Disponible sur Internet : <https://books.openedition.org/aaccademia/8203>. ISBN : 979-12-80136-33-6. DOI : https://doi.org/10.4000/books.aaccademia.8203.Dell'Orletta, F., Monti, J., & Tamburini, F. (Eds.) 2020. Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020 : Bologna, Italy, March 1-3, 2021. Torino : Accademia University Press. doi :10.4000/books.aaccademia.8203Dell'Orletta, Felice, et al., ed. Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020 : Bologna, Italy, March 1-3, 2021. Torino : Accademia University Press, 2020. Web. <https://books.openedition.org/aaccademia/8203>.Compatible avec Zotero - Partager URL :
- Courriel
Collez le code html suivant pour intégrer ce livre sur votre site.
Distributional Semantics: Yesterday, Today, and Tomorrow
1Distributional semantics is undoubtedly the mainstream approach to meaning representation in computational linguistics today. It has also become an important paradigm of semantic analysis in cognitive science, and even linguists have started looking at it with growing interest. The popularity of distributional semantics has literally boomed in the era of Deep Learning, when “word embeddings” have become the basic ingredient to “cook” any NLP task. The era of BERT & co. has brought new types of contextualized representations that have often generated hasty claims of incredible breakthroughs in the natural language understanding capability of deep learning models. Unfortunately, these claims are not always supported by the improved semantic abilities of the last generation of embeddings. Models like BERT are still rooted in the principles of distributional learning, but at the same time their goal is more ambitious than generating corpus-based representations of meaning. On the one hand, the embeddings they produce encode much more than lexical meaning, but on the other hand we are still largely uncertain about what semantic properties of natural language they actually capture. Distributional semantics has surely benefited from the successes of the deep learning, but this might even jeopardize the very essence of distributional models of meaning, by making their goals and foundations unclear.
2Computational linguistics is a fast-moving field and distributional semantics makes no exception. In doing this, we always risk chasing the last hype model or using pre-trained vectors as black-box tools, without scrutinizing the relationship between distributional learning and meaning representations. The goal of this tutorial is to try to understand what distributional semantics is today, by looking also at what it was yesterday and at its grounding principles. I will present the main concepts, tools and applications of distributional semantics, to foster a critical analysis of its potentialities as well as its limits. This way, we will try to imagine what distributional semantic could and should become tomorrow.
Auteur
Alessandro Lenci
University of Pisa – alessandro.lenci@unipi.it