The SenSE Toolkit: A System for Visualization and Explanation of Semantic Shift

Maurício Gruppi, Sibel Adalı, Pin-Yu Chen
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, PMLR 176:283-287, 2022.

Abstract

Lexical Semantic Change (LSC) detection, also known as Semantic Shift, is the process of identifying and characterizing variations in language usage across different scenarios such as time and domain. It allows us to track the evolution of word senses, as well as to understand the difference between the languages used by distinct communities. LSC detection is often done by applying a distance measure over vectors of two aligned word embedding matrices. In this paper, we present SenSE, an interactive semantic shift exploration toolkit that provides visualization and explanation of lexical semantic change for an input pair of text sources. Our system focuses on showing how the different alignment strategies may affect the output of an LSC model as well as on explaining semantic change based on the neighbors of a chosen target word, while also extracting examples of sentences where these semantic deviations appear. The system runs as a web application (available at \url{http://sense.mgruppi.me}), allowing the audience to interact by configuring the alignment strategies while visualizing the results in a web browser.

Cite this Paper

BibTeX
@InProceedings{pmlr-v176-gruppi22a, title = {The SenSE Toolkit: A System for Visualization and Explanation of Semantic Shift}, author = {Gruppi, Maur\'{i}cio and Adal\i, Sibel and Chen, Pin-Yu}, booktitle = {Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track}, pages = {283--287}, year = {2022}, editor = {Kiela, Douwe and Ciccone, Marco and Caputo, Barbara}, volume = {176}, series = {Proceedings of Machine Learning Research}, month = {06--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v176/gruppi22a/gruppi22a.pdf}, url = {https://proceedings.mlr.press/v176/gruppi22a.html}, abstract = { Lexical Semantic Change (LSC) detection, also known as Semantic Shift, is the process of identifying and characterizing variations in language usage across different scenarios such as time and domain. It allows us to track the evolution of word senses, as well as to understand the difference between the languages used by distinct communities. LSC detection is often done by applying a distance measure over vectors of two aligned word embedding matrices. In this paper, we present SenSE, an interactive semantic shift exploration toolkit that provides visualization and explanation of lexical semantic change for an input pair of text sources. Our system focuses on showing how the different alignment strategies may affect the output of an LSC model as well as on explaining semantic change based on the neighbors of a chosen target word, while also extracting examples of sentences where these semantic deviations appear. The system runs as a web application (available at \url{http://sense.mgruppi.me}), allowing the audience to interact by configuring the alignment strategies while visualizing the results in a web browser.} }
Endnote
%0 Conference Paper %T The SenSE Toolkit: A System for Visualization and Explanation of Semantic Shift %A Maurício Gruppi %A Sibel Adalı %A Pin-Yu Chen %B Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track %C Proceedings of Machine Learning Research %D 2022 %E Douwe Kiela %E Marco Ciccone %E Barbara Caputo %F pmlr-v176-gruppi22a %I PMLR %P 283--287 %U https://proceedings.mlr.press/v176/gruppi22a.html %V 176 %X Lexical Semantic Change (LSC) detection, also known as Semantic Shift, is the process of identifying and characterizing variations in language usage across different scenarios such as time and domain. It allows us to track the evolution of word senses, as well as to understand the difference between the languages used by distinct communities. LSC detection is often done by applying a distance measure over vectors of two aligned word embedding matrices. In this paper, we present SenSE, an interactive semantic shift exploration toolkit that provides visualization and explanation of lexical semantic change for an input pair of text sources. Our system focuses on showing how the different alignment strategies may affect the output of an LSC model as well as on explaining semantic change based on the neighbors of a chosen target word, while also extracting examples of sentences where these semantic deviations appear. The system runs as a web application (available at \url{http://sense.mgruppi.me}), allowing the audience to interact by configuring the alignment strategies while visualizing the results in a web browser.
APA
Gruppi, M., Adalı, S. & Chen, P.. (2022). The SenSE Toolkit: A System for Visualization and Explanation of Semantic Shift. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, in Proceedings of Machine Learning Research 176:283-287 Available from https://proceedings.mlr.press/v176/gruppi22a.html.

Related Material