Named Entity Recognition to Detect Criminal Texts on the Web

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 623–632 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 623 On the Impact of Temporal Representations on Metaphor Detection Giorgio Ottolina, Matteo Palmonari, Manuel Vimercati, Mehwish Alam University of Milano-Bicocca, Milan, Italy FIZ Karlsruhe - Leibniz Institute for Information Infrastructure, Karlsruhe, Germany g.ottolina1@campus.unimib.it, {matteo.palmonari, manuel.vimercati}@unimib.it, mehwish.alam@fiz-karlsruhe.de Abstract State-of-the-art approaches for metaphor detection compare their literal - or core - meaning and their contextual meaning using metaphor classifiers based on neural networks. However, metaphorical expressions evolve over time due to various reasons, such as cultural and societal impact. Metaphorical expressions are known to co-evolve with language and literal word meanings, and even drive, to some extent, this evolution. This poses the question of whether different, possibly time-specific, representations of literal meanings may impact the metaphor detection task. To the best of our knowledge, this is the first study that examines the metaphor detection task with a detailed exploratory analysis where different temporal and static word embeddings are used to account for different representations of literal meanings. Our experimental analysis is based on three popular benchmarks used for metaphor detection and word embeddings extracted from different corpora and temporally aligned using different state-of-the-art approaches. The results suggest that the usage of different static word embedding methods does impact the metaphor detection task and some temporal word embeddings slightly outperform static methods. However, the results also suggest that temporal word embeddings may provide representations of the core meaning of the metaphor even too close to their contextual meaning, thus confusing the classifier. Overall, the interaction between temporal language evolution and metaphor detection appears tiny in the benchmark datasets used in our experiments. This suggests that future work for the computational analysis of this important linguistic phenomenon should first start by creating a new dataset where this interaction is better represented. Keywords: Metaphor Detection, Temporal Word Embeddings, Static Word Embeddings 1. Introduction Accounting for figurative language is one of the key challenges in Natural Language Processing (NLP) (Re- forgiato Recupero et al., 2019; Shutova, 2015). Figura- tive language often contains metaphorical expressions which map one concept from a source domain to an- other concept in a target domain. For instance, in the sentence “The wheels of Stalin’s regime were well-oiled and already turning”, a political system (target con- cept) is viewed in terms of a mechanism (source con- cept) that can function, break, have wheels, etc. This association allows us to transfer knowledge from the domain of mechanical engineering to that of politics. Therefore, political systems are thought about in terms of mechanisms, leading to multiple metaphorical ex- pressions. The phenomenon of source-target domain mapping was first introduced by George Lakoff known as Conceptual Metaphor Theory (Lakoff and Johnson, 1980). Due to previously defined characteristics, the presence of metaphorical expression in text causes mis- interpretation in the algorithms such as machine trans- lation or sentiment analysis (Mohammad et al., 2016). Recent studies addressing the metaphor detection …

Content truncated to 500 words