Published June 11, 2026 | Version v1

TASC: Topical-Aware Semantic Change

Authors/Creators

Description

Cache files of TASC's sample data from the SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection dataset.

It contains .npz files containing the occurrences of the 37 target lemmas in each corpus ("targeted_words") and the embeddings of these occurrences ("all-mpnet-base-v2-L11"), as well as the top2vec model in a .pkl file.

Files

Files (1.5 GB)

Name Size
md5:697859686bf97a9a2738d36f65a7136f
807.0 MB Download
md5:40b90d66d0716a70e392843c752a2f56
521.0 kB Download
md5:b2511d29c842207d5edf21506b46be4f
605.4 MB Download
md5:ec07df51677e446ca244038b594c5c86
409.7 kB Download
md5:01f1e3a06b797e20bd0bbf0de83d41e9
74.0 MB Download

Additional details

Software

Repository URL
https://github.com/tobiia/TASC
Programming language
Python
Development Status
Active