TopoAct: Visually exploring the shape of activations in deep learning

A Rathore, N Chalapathi, S Palande… - Computer Graphics …, 2021 - Wiley Online Library
Deep neural networks such as GoogLeNet, ResNet, and BERT have achieved impressive
performance in tasks such as image and text classification. To understand how such …

Draw mir a Sheep: A Supersense-based Analysis of German Case and Adposition Semantics

J Prange, N Schneider - KI-Künstliche Intelligenz, 2021 - Springer
Adpositions and case markers are ubiquitous in natural language and express a wide range
of meaning relations that can be of crucial relevance for many NLP and AI tasks. However …

My case, for an adposition: Lexical polysemy of adpositions and case markers in Finnish and Latin

D Chen, M Hulden - … of the Thirteenth Language Resources and …, 2022 - aclanthology.org
Adpositions and case markers contain a high degree of polysemy and participate in unique
semantic role configurations. We present a novel application of the SNACS supersense …

A corpus of adpositional supersenses for Mandarin Chinese

S Peng, Y Liu, Y Zhu, A Blodgett, Y Zhao… - arXiv preprint arXiv …, 2020 - arxiv.org
Adpositions are frequent markers of semantic relations, but they are highly ambiguous and
vary significantly from language to language. Moreover, there is a dearth of annotated …

Putting Context in SNACS: A 5-Way Classification of Adpositional Pragmatic Markers

YJ Liu, JD Hwang, N Schneider… - Proceedings of the 16th …, 2022 - aclanthology.org
The SNACS framework provides a network of semantic labels called supersenses for
annotating adpositional semantics in corpora. In this work, we consider English prepositions …

[PDF][PDF] MASALA: Modelling and Analysing the Semantics of Adpositions in Linguistic Annotation of Hindi

AANVN Schneider - lrec-conf.org
● Hindi (and Urdu) has a complex inventory of case markers and postpositions for marking
semantic relations between words○ Case markers: small set of markers that indicate core …