Comparing Machine Learning and Deep Learning Approaches on NLP Tasks for the Italian Language

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 2110–2119 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 2110 Comparing Machine Learning and Deep Learning Approaches on NLP Tasks for the Italian Language Bernardo Magnini, Alberto Lavelli, Simone Magnolini Fondazione Bruno Kessler via Sommarive 18, Povo - Trento (ITALY) {magnini, lavelli, magnolini}@fbk.eu Abstract We present a comparison between deep learning and traditional machine learning methods for various NLP tasks in Italian. We carried on experiments using available datasets (e.g., from the Evalita shared tasks) on two sequence tagging tasks (i.e., named entity recognition and nominal entity recognition) and four classification tasks (i.e., lexical relations among words, semantic relations among sentences, sentiment analysis and text classification). We show that deep learning approaches outperform traditional machine learning algorithms in sequence tagging, while for classification tasks that heavily rely on semantics approaches based on feature engineering are still competitive. We think that a similar analysis could be carried out for other languages to provide an assessment of machine learning / deep learning models across different languages. Keywords: Machine Learning, Deep Learning, Italian Language 1. Introduction In the recent years, the so called ”deep learning revolution” has influenced and changed many fields of Artificial Intelli- gence (e.g., machine learning and computer vision) and has also affected all areas related to human language technolo- gies. Initial results have been obtained with the adoption of deep neural networks in speech recognition, with a sig- nificant boost of performance in automatic speech recogni- tion systems (Graves et al., 2013). In Machine Translation, starting from 2013, the phrase-based statistical approaches that were at the state of the art have been gradually substi- tuted with neural machine translation, based on deep learn- ing architectures, which have been proven to obtain bet- ter performance (Bahdanau et al., 2014). The main reason for this increase in performance is that, as more training data are available both for speech recognition and machine translation, large neural networks have been proven to be superior to traditional machine learning (ML) algorithms, such as support vector machines. However, if we consider tasks related to semantic analy- sis of text, the limited availability of semantically anno- tated data, typically requiring specialized human effort, has slowed the adoption of neural approaches. It is only in the last few years that deep learning has obtained high perfor- mance across different NLP tasks. These models can often be trained with a single end-to-end model and do not re- quire task-specific feature engineering, thus they not only tend to perform better than traditional ML, but they do re- quire less human effort, making their adoption convenient. In this paper we provide a comparison between traditional approaches and deep learn- ing applied to NLP tasks in the area of information extrac- tion from Italian texts. We carried on experiments using available datasets on both sequence tagging (i.e., named entity recognition, nominal entity recognition) and classi- fication tasks (i.e., lexical relations among words, semantic …

Content truncated to 500 words