stp2y

arXiv:2408.03070v1 Announce Type: new Abstract: Contradictory results about the encoding of the semantic impact of negation in pretrained language models (PLMs). have been drawn recently (e.g. Kassner and Sch{"u}tze (2020); Gubelmann and Handschuh (2022)). In this paper we focus rather on the way PLMs encode negation and its formal impact, through the phenomenon of the Negative Polarity Item (NPI) licensing in English. More precisely, we use probes to identify which contextual representations best encode 1) the presence of negation in a sentence, and 2) the polarity of a neighboring masked polarity item. We find that contextual representations of tokens inside…

(Andrey_Popov/Shutterstock) It sounded like it was going to be a good meeting. The data science team briefed company leadership on what the data said about a proposed cost-cutting initiative, excitedly revealing findings that took them a few weeks to pull together due to the dozens of similar mission-critical requests they received. But by the meeting’s end, the execs around the conference table realized the team, through no fault of their own, has left behind as many questions as answers: Switching up the supply chain is risky, can we be sure about the tradeoff? Will cutting sales headcount hurt us more…

arXiv:2408.02695v1 Announce Type: new Abstract: Continual Learning (CL) aims to enable Deep Neural Networks (DNNs) to learn new data without forgetting previously learned knowledge. The key to achieving this goal is to avoid confusion at the feature level, i.e., avoiding confusion within old tasks and between new and old tasks. Previous prototype-based CL methods generate pseudo features for old knowledge replay by adding Gaussian noise to the centroids of old classes. However, the distribution in the feature space exhibits anisotropy during the incremental process, which prevents the pseudo features from faithfully reproducing the distribution of old knowledge in the feature…