QMUL-SDS @ DIACR-Ita: Evaluating Unsupervised Diachronic Lexical Semantics Classification in Italian
This work addresses the problem of tracking word meaning changes over time in Italian for computational linguistics, but it is incremental as it applies existing methods to a specific dataset and task.
The paper tackled the task of unsupervised diachronic lexical semantics classification in Italian by evaluating different training sets and semantic detection methods, achieving 83.3% accuracy and ranking 3rd in the DIACR-ITA 2020 competition.
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 Network using accuracy. Our model ranked 3rd with an accuracy of 83.3%.