UPDF AI

An Assessment of Experimental Protocols for Tracing Changes in Word Semantics Relative to Accuracy and Reliability

Johannes Hellrich,U. Hahn

2016 · DOI: 10.18653/v1/W16-2114
14 Citations

TLDR

This research investigated two well-known training protocols for neural language models in a synchronic experiment and identified critical parameters for improving the underlying protocols in order to generate more adequate diachronic language models.

Abstract

Our research aims at tracking the semantic evolution of the lexicon over time. For this purpose, we investigated two well-known training protocols for neural language models in a synchronic experiment and encountered several problems relating to accuracy and reliability. We were able to identify critical parameters for improving the underlying protocols in order to generate more adequate diachronic language models.