Search

The eighth edition of the Italian Conference on Computational Linguistics (CLiC-it 2021) was held at Università degli Studi di Milano-Bicocca from 26th to 28th January 2022. After the edition of 2020, which was held in fully virtual mode due to the health emergency related to Covid-19, CLiC-it 2021 represented the first moment for the Italian research community of Computational Linguistics to meet in person after more than one year of full/partial lockdown.

Part-of-speech (PoS) tagging constitutes a common task in Natural Language Processing (NLP) given its widespread applicability. However, with the advance of new information technologies and language variation, the contents and methods for PoS-tagging have changed. The majority of Italian existing data for this task originate from standard texts, where language use is far from multifaceted informal real-life situations. Automatic PoS-tagging models trained with such data do not perform reliably on non-standard language, like social media content or language learners’ texts. Our aim is to provide additional training and evaluation data from language learners tagged in Universal Dependencies (UD), as well as testing current automatic PoS-tagging systems and evaluating their performance on such data. We use Italian texts from a multilingual corpus of young language learners, LEONIDE, to create a tagged gold standard for evaluating UD PoS-tagging performance on non-standard language. With the 3.7 version of Stanza, a Python NLP package, we apply available automatic PoS-taggers, namely ISDT, ParTUT, POSTWITA, TWITTIRÒ and VIT, trained with diversified data, on our dataset. Our results show that the above taggers, trained on non-standard data or multilingual treebanks, can achieve up to 95% of accuracy on young multilingual learner data, if combined.

Part-of-speech (PoS) tagging constitutes a common task in Natural Language Processing (NLP) given its widespread applicability. However, with the advance of new information technologies and language variation, the contents and methods for PoS-tagging have changed. The majority of Italian existing data for this task originate from standard texts, where language use is far from multifaceted informal real-life situations. Automatic PoS-tagging models trained with such data do not perform reliably on non-standard language, like social media content or language learners’ texts. Our aim is to provide additional training and evaluation data from language learners tagged in Universal Dependencies (UD), as well as testing current automatic PoStagging systems and evaluating their performance on such data. We use Italian texts from a multilingual corpus of young language learners, LEONIDE, to create a tagged gold standard for evaluating UD PoS-tagging performance on nonstandard language. With the 3.7 version of Stanza, a Python NLP package, we apply available automatic PoS-taggers, namely ISDT, ParTUT, POSTWITA, TWITTIRÒ, and VIT, trained with diversified data, on our dataset. Our results show that the above taggers, trained on non-standard data or multilingual treebanks, can achieve up to 95% of accuracy on young multilingual learner data, if combined. ispartof: pages:1-7 ispartof: http://ceur-ws.org/Vol-3033/ pages:1-7 ispartof: CLiC-it 2021 Italian Conference on Computational Linguistics 2021 location:Milan status: Published online

The automatic assessment of language learners’ competences represents an increasingly promising task thanks to recent developments in NLP and deep learning technologies. In this paper, we propose the use of neural models for classifying English written exams into one of the Common European Framework of Reference for Languages (CEFR) competence levels. We employ pre-trained Bidirectional Encoder Representations from Transformers (BERT) models which provide efficient and rapid language processing on account of attention-based mechanisms and the capacity of capturing long-range sequence features. In particular, we investigate augmenting the original learner’s text with corrections provided by an automatic tool or by human evaluators. We consider different architectures where the texts and corrections are combined at an early stage, via concatenation before the BERT network, or as late fusion of the BERT embeddings. The proposed approach is evaluated on two open-source datasets: the English First Cambridge open language Database (EFCAMDAT) and the Cambridge Learner Corpus for the First Certificate in English (CLC-FCE). The experimental results show that the proposed approach can predict the learner’s competence level with remarkably high accuracy, in particular when large labeled corpora are available. In addition, we observed that augmenting the input text with corrections provides further improvement in the automatic language assessment task. ispartof: http://ceur-ws.org/Vol-3033/ vol:3033 ispartof: CLiC-it 2021 Italian Conference on Computational Linguistics 2021 location:Milan status: Published online