Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarials

In recent years, large language models have achieved state-of-the-art performance across various NLP tasks. However, investigations have shown that these models tend to rely on shortcut features, leading to inaccurate predictions and causing the models to be unreliable at generalization to out-of-distribution (OOD) samples. For instance, in the context of relation extraction (RE), we would expect a model to identify the same relation independently of the entities involved in it. For example, consider the sentence "Leonardo da Vinci painted the Mona Lisa" expressing the created(Leonardo_da_Vinci, Mona_Lisa) relation. If we substiute "Leonardo da Vinci" with "Barack Obama", then the sentence still expresses the created relation. A robust model is supposed to detect the same relation in both cases. In this work, we describe several semantically-motivated strategies to generate adversarial examples by replacing entity mentions and investigate how state-of-the-art RE models perform under pressure. Our analyses show that the performance of these models significantly deteriorates on the modified datasets (avg. of -48.5% in F1), which indicates that these models rely to a great extent on shortcuts, such as surface forms (or patterns therein) of entities, without making full use of the information present in the sentences.

#LaCulturaNonsiFerma: Report on Use and Diffusion of #Hashtags from the Italian Cultural Institutions during the COVID-19 outbreak

This report presents an analysis of #hashtags used by Italian Cultural Heritage institutions to promote and communicate cultural content during the COVID-19 lock-down period in Italy. Several activities to support and engage users' have been proposed using social media. Most of these activities present one or more #hashtags which help to aggregate content and create a community on specific topics. Results show that on one side Italian institutions have been very proactive in adapting to the pandemic scenario and on the other side users' reacted very positively increasing their participation in the proposed activities.

LaCulturaNonSiFerma -- Report su uso e la diffusione degli hashtag delle istituzioni culturali italiane durante il periodo di lockdown

This report presents an analysis of #hashtags used by Italian Cultural Heritage institutions to promote and communicate cultural content during the COVID-19 lock-down period in Italy. Several activities to support and engage users' have been proposed using social media. Most of these activities present one or more #hashtags which help to aggregate content and create a community on specific topics. Results show that on one side Italian institutions have been very proactive in adapting to the pandemic scenario and on the other side users' reacted very positively increasing their participation in the proposed activities.