Grammatical Profiling for Semantic Change Detection

09/21/2021
by   Mario Giulianelli, et al.
0

Semantics, morphology and syntax are strongly interdependent. However, the majority of computational methods for semantic change detection use distributional word representations which encode mostly semantics. We investigate an alternative method, grammatical profiling, based entirely on changes in the morphosyntactic behaviour of words. We demonstrate that it can be used for semantic change detection and even outperforms some distributional semantic methods. We present an in-depth qualitative and quantitative analysis of the predictions made by our grammatical profiling system, showing that they are plausible and interpretable.

READ FULL TEXT
research
07/24/2019

Distributional Analysis of Function Words

This paper is a first attempt at reconciling the current methods of dist...
research
08/31/2022

Contextualized language models for semantic change detection: lessons learned

We present a qualitative analysis of the (potentially erroneous) outputs...
research
05/03/2021

Semantic Journeys: Quantifying Change in Emoji Meaning from 2012-2018

The semantics of emoji has, to date, been considered from a static persp...
research
09/21/2019

Generating Timelines by Modeling Semantic Change

Though languages can evolve slowly, they can also react strongly to dram...
research
01/15/2019

Investigating Antigram Behaviour using Distributional Semantics

Language is an extremely interesting subject to study, each day presenti...
research
04/02/2018

Modeling Semantic Plausibility by Injecting World Knowledge

Distributional data tells us that a man can swallow candy, but not that ...
research
04/20/2021

Novel Aficionados and Doppelgängers: a referential task for semantic representations of individual entities

In human semantic cognition, proper names (names which refer to individu...

Please sign up or login with your details

Forgot password? Click here to reset