QMUL-SDS @ DIACR-Ita: Evaluating Unsupervised Diachronic Lexical Semantics Classification in Italian [article]

Rabab Alkhalifa, Adam Tsakalidis, Arkaitz Zubiaga, Maria Liakata
2020 arXiv   pre-print
In this paper, we present the results and main findings of our system for the DIACR-ITA 2020 Task. Our system focuses on using variations of training sets and different semantic detection methods. The task involves training, aligning and predicting a word's vector change from two diachronic Italian corpora. We demonstrate that using Temporal Word Embeddings with a Compass C-BOW model is more effective compared to different approaches including Logistic Regression and a Feed Forward Neural
more » ... k using accuracy. Our model ranked 3rd with an accuracy of 83.3%.
arXiv:2011.02935v2 fatcat:ftz3tdcerfcu3ojfisrzvyr2oa