Scheda libro

IJCoL - Italian Journal of Computational Linguistics

IJCoL - Italian Journal of Computational Linguistics vol. 6, n. 1 june 2020
vol. 6, n. 1

a cura di Roberto Basili, Simonetta Montemagni

anno di pubblicazione 2020
pp. 97
ISBN pdf 9791280136404
DOI 10.4000/ijcol.606

Il primo numero del sesto anno della rivista Italian Journal of Computational Linguistics (IJCoL), la rivista italiana promossa dall’Associazione Italiana di Linguistica Computazionale (AILC - www.ai-lc.it), è un volume miscellaneo i cui articoli documentano linee di ricerca attive nel panorama della Linguistica Computazionale italiana con risultati interessanti. Gli articoli raccolti in questo volume documentano una prima selezione di lavori di ricerca risultati particolarmente promettenti nell’ambito della sesta Conferenza CLiC-it, tenutasi a Bari, dal 13 al 15 novembre 2019. Tutti i contributi sono stati sottoposti a un processo di peer-review iterativo, prima nell’ambito della conferenza, poi come candidati ai premi di “Best Young Paper” e “Distinguished Young Paper”, infine come contributo su rivista.
I temi affrontati coprono sviluppi recenti e fecondi della ricerca in linguistica computazionale, che vanno dalla costruzione di modelli e algoritmi cognitivamente motivati per l’analisi del significato, all’utilizzo di ''word embeddings'' per studi diacronici del lessico della lingua latina e a metodi di profilazione linguistica applicati a generi testuali e registri linguistici, per giungere all’applicazione di metodi e tecniche sviluppate in ambito linguistico-computazionale all’interno di diversi scenari, che spaziano dalla sottotitolazione di film al riconoscimento di espressioni di odio.

bio articoli

Roberto Basili, Università di Roma Tor Vergata.

Simonetta Montemagni, Istituto di Linguistica Computazionale “Antonio Zampolli”, CNR.

Basili - Montemagni, Editorial Note
	pdf 88.2 KB	DOI 10.4000/ijcol.608	IJCoL_6_1_01_EditorialNote	0,00 €	IJCoL_6_1_01_EditorialNote"
Preissner - Herbelot, Biodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm
	pdf 845.2 KB ABSTRACT ↗ The natural world is very diverse in terms of biological organisation, and solves problems in a wide variety of efficient and creative manners. This biodiversity is in stark contrast with the landscape of artificial models in the field of Natural Language Processing (NLP). In the last years, NLP algorithms have clustered around a few very expensive architectures, the cost of which has many facets, including training times, storage, replicability, interpretability, equality of access to experimental paradigms, and even environmental impact. Inspired by the biodiversity of the real world, we argue for a methodology which promotes ‘artificial diversity’, and we further propose that cognitively-inspired algorithms are a good starting point to explore new architectures. As a case study, we investigate the fruit fly’s olfactory system as a distributional semantics model. We show that, even in its rawest form, it provides many of the features that we might require from a good model of meaning acquisition, and that the original architecture can serve as a basis for cognitively-inspired extensions. We focus on one such extension by implementing a mechanism of neural adaptation.	DOI 10.4000/ijcol.609	IJCoL_6_1_02_Preissner_Herbelo	0,00 €	IJCoL_6_1_02_Preissner_Herbelo"
Sprugnoli - Moretti - Passarotti, Building and Comparing Lemma Embeddings for Latin. Classical Latin versus Thomas Aquinas
	pdf 172.3 KB ABSTRACT ↗ This paper presents a new set of lemma embeddings for the Latin language. Embeddings are trained on a manually annotated corpus of texts belonging to the Classical era: different models, architectures and dimensions are tested and evaluated using a novel benchmark for the synonym selection task. In addition, we release vectors pre-trained on the “Opera Maiora” by Thomas Aquinas, thus providing a resource to analyze Latin in a diachronic perspective. The embeddings built upon the two training corpora are compared to each other to support diachronic lexical studies. The words showing the highest usage change between the two corpora are reported and a selection of them is discussed.	DOI 10.4000/ijcol.624	IJCoL_6_1_03_Sprugnoli_Moretti	0,00 €	IJCoL_6_1_03_Sprugnoli_Moretti"
Buongiovanni - Gracci - Brunato - Dell’Orletta, Lost in Text: A Cross-Genre Analysis of Linguistic Phenomena within Text
	pdf 1.2 MB ABSTRACT ↗ Moving from the assumption that formal, rather than content features, can be used to detect differences and similarities among textual genres and registers, this paper presents a new approach to linguistic profiling – a well-established methodological framework to study language variation – which is applied to detect significant variations within the internal structure of a text. We test this approach on the Italian language using a wide spectrum of linguistic features automatically extracted from parsed corpora representative of four main genres and two levels of complexity for each, and we show that it is possible to model the degree of stylistic variance within texts according to genre and language complexity.	DOI 10.4000/ijcol.634	IJCoL_6_1_04_Buongiovanni_Grac	0,00 €	IJCoL_6_1_04_Buongiovanni_Grac"
Karakanta - Negri - Turchi, Towards Automatic Subtitling: Assessing the Quality of Old and New Resources
	pdf 305 KB ABSTRACT ↗ Growing needs in localising multimedia content for global audiences have resulted in Neural Machine Translation (NMT) gradually becoming an established practice in the field of subtitling in order to reduce costs and turn-around times. Contrary to text translation, subtitling is subject to spatial and temporal constraints, which greatly increase the post-processing effort required to restore the NMT output to a proper subtitle format. In our previous work (Karakanta, Negri, and Turchi 2019), we identified several missing elements in the corpora available for training NMT systems specifically tailored for subtitling. In this work, we compare the previously studied corpora with MuST-Cinema, a corpus enabling end-to-end speech to subtitles translation, in terms of the conformity to the constraints of: 1) length and reading speed; and 2) proper line breaks. We show that MuST-Cinema conforms to these constraints and discuss the recent progress the corpus has facilitated in end-to-end speech to subtitles translation.	DOI 10.4000/ijcol.649	IJCoL_6_1_05_Karakanta_Negri_T	0,00 €	IJCoL_6_1_05_Karakanta_Negri_T"
AA.VV., “Contro L’Odio”: A Platform for Detecting, Monitoring and Visualizing Hate Speech against Immigrants in Italian Social Media
	pdf 1.7 MB ABSTRACT ↗ The paper describes the Web platform built within the project “Contro l’Odio”, for monitoring and contrasting discrimination and hate speech against immigrants in Italy. It applies a combination of computational linguistics techniques for hate speech detection and data visualization tools on data drawn from Twitter. It allows users to access a huge amount of information through interactive maps, also tuning their view, e.g. visualizing the most viral tweets and interactively reducing the inherent complexity of data. Educational courses for high school students have been developed which are centered on the platform and focused on the deconstruction of negative stereotypes against immigrants, Rom and religious minorities, and on the creation of positive narratives. The data collected and analyzed by the platform are also currently used for benchmarking activities within an evaluation campaign, and for paving the way to new projects against hate.	DOI 10.4000/ijcol.659	IJCoL_6_1_06_AA.VV	0,00 €	IJCoL_6_1_06_AA.VV"

FACEBOOK

INSTAGRAM