Search results for "NLP"
showing 10 items of 24 documents
Development of statistical methods for the analysis of textual data
2022
Overview of the Evalita 2014 SENTIment POLarity Classification Task
2014
International audience; English. The SENTIment POLarity Classification Task (SENTIPOLC), a new shared task in the Evalita evaluation campaign , focused on sentiment classification at the message level on Italian tweets. It included three subtasks: subjectivity classification, polarity classification, and irony detection. SENTIPOLC was the most participated Evalita task with a total of 35 submitted runs from 11 different teams. We present the datasets and the evaluation methodology, and discuss results and participating systems. Italiano. Descriviamo modalit a e risultati della campagna di valutazione di sistemi di sentiment analysis (SENTIment POLarity Classification Task), proposta per la …
Mind Games
2021
This paper describes the preliminary stages and the theoretical and methodological inspiration for the design of UrbanCraft, a gamified activity based on Kevin Lynch's mental maps and aiming at enhancing youth participation and inclusion in urban co-design and governance. This activity draws on previous local experiences on participation and social inclusion, held in the Southern Italian city of Palermo, in an attempt to mix urban studies, serious games and artificial intelligence methodologies. In this experiment, we designed a gamified activity conceived for nine- to twelve-year-old primary and secondary school children, due to our previous cooperation with several primary and secondary s…
McRock at SemEval-2022 Task 4: Patronizing and Condescending Language Detection using Multi-Channel CNN, Hybrid LSTM, DistilBERT and XLNet
2022
In this paper we propose four deep learning models for the task of detecting and classifying Patronizing and Condescending Language (PCL) using a corpus of over 13,000 annotated paragraphs in English. The task, hosted at SemEval-2022, consists of two different subtasks. The Subtask 1 is a binary classification problem. Namely, given a paragraph, a system must predict whether or not it contains any form of PCL. The Subtask 2 is a multi-label classification task. Given a paragraph, a system must identify which PCL categories express the condescension. A paragraph might contain one or more categories of PCL. To face with the first subtask we propose a multi-channel Convolutional Neural Network…
Fake News Spreaders Detection: Sometimes Attention Is Not All You Need
2022
Guided by a corpus linguistics approach, in this article we present a comparative evaluation of State-of-the-Art (SotA) models, with a special focus on Transformers, to address the task of Fake News Spreaders (i.e., users that share Fake News) detection. First, we explore the reference multilingual dataset for the considered task, exploiting corpus linguistics techniques, such as chi-square test, keywords and Word Sketch. Second, we perform experiments on several models for Natural Language Processing. Third, we perform a comparative evaluation using the most recent Transformer-based models (RoBERTa, DistilBERT, BERT, XLNet, ELECTRA, Longformer) and other deep and non-deep SotA models (CNN,…
Supporting Emotion Automatic Detection and Analysis over Real-Life Text Corpora via Deep Learning: Model, Methodology, and Framework
2021
This paper describes an approach for supporting automatic satire detection through effective deep learning (DL) architecture that has been shown to be useful for addressing sarcasm/irony detection problems. We both trained and tested the system exploiting articles derived from two important satiric blogs, Lercio and IlFattoQuotidiano, and significant Italian newspapers.
Strukturētu datu vizualizācija, pamatojoties uz definīciju dabīgā valodā
2017
Bakalaura darbs apskata sekojošu problēmu: datu vizualizācija, pamatojoties uz definīciju dabīgā valodā. Par pamatu tiek ņemta populāra biznesa analītikas platforma un tiek mēģināts attīstīt to, pievienojot dabīgas valodas apstrādes iespējas. Darba ietvaros tika veikta esošo risinājumu analīze ar mērķi atrast šo risinājumu nepilnības un ieverot tos sistēmas izstrādāšanā. Balstoties uz šo analīzi, kā arī uz eksistējošas biznesa analītikas platformas iespējām, tika izveidota sistēma, kas saņem lietotāja definīciju vai pieprasījumu dabīgā valodā, apstrādā to izmantojot dabīgas valodas apstrādes algoritmus un mašīnmācīšanās iespējas un atgriež interaktīvu datu vizualizāciju. Izstrādātā sistēma …
Propaganda Barometer : A Supportive Tool to Improve Media Literacy Towards Building a Critically Thinking Society
2018
To smartly consume a huge and constantly growing volume of information, to identify fake news and resist propaganda in the context of Information Warfare, to improve personal critical thinking capabilities and increase media literacy, people require supportive environment with sophisticated technology facilitated tools. With rapid development of media, widespread popularity of social networks and fast growing amount of information distribution channels, propaganda and information warfare enter an absolutely new digital technology supported cyber era. Propaganda mining is not a trivial and very time consuming process for human. And, as with any new technology, human need certain time to unde…
Luonnollisten kielten kääntäminen ja konekäännös - Taustaa, teoriaa ja menetelmiä
2010
López, Elina I. Tietojärjestelmätieteen kandidaatintutkielma / Elina I. López Jyväskylä: Jyväskylän yliopisto, 2010. 36 s. Luonnollisten kielten kääntäminen on olennainen osa ihmisten elämää, erityi-sesti nykyisessä kansainvälisessä maailmassa. Ilman kääntämistä eivät esimer-kiksi yritykset pysty toimimaan. Käännettävät tekstimassat kuitenkin kasvavat kasvamistaan ja käännöstyön nopeuttamiseksi on haettu apua tietokoneista. Konekääntämistä onkin tutkittu ensimmäisten tietokoneiden käyttöönotosta lähtien. Tässä tutkielmassa käsitellään luonnollisia kieliä, perinteistä kääntämistä ja ko-nekäännöksiä. Tutkielmassa käydään läpi luonnollisten kielten jaotteluita ja ominaisuuksia, jotka tekevät …
Spatial Cognition 2020/1: Book of abstracts : August 2-4, 2021, University of Latvia
2021
Spatial Cognition is concerned with the acquisition, development, representation, organization, and use of knowledge about spatial objects in real, virtual or hybrid environments and processed by human or artificial agents. Spatial Cognition includes research from different fields insofar as they are concerned with cognitive agents and space, such as cognitive and developmental psychology, linguistics, computer science, geography, cartography, philosophy, neuroscience, and education. Research issues in the field range from the investigation of human spatial cognition to mobile robot navigation, including topics such as wayfinding, spatial planning, spatial learning, internal and external re…