# CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations

arXiv: https://arxiv.org/abs/2005.06602 · HTML: https://mlsanity.com/paper/2005.06602/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 9 of 9)

- [A Survey on Contextualised Semantic Shift Detection](https://mlsanity.com/paper/2304.01666/) (2023)
- [A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change](https://mlsanity.com/paper/2402.12011/) (2024)
- [Lexical Semantic Change Discovery](https://mlsanity.com/paper/2106.03111/) (2021)
- [LSCDiscovery: A shared task on semantic change discovery and detection in Spanish](https://mlsanity.com/paper/2205.06691/) (2022)
- [Graph-based Clustering for Detecting Semantic Change Across Time and Languages](https://mlsanity.com/paper/2402.01025/) (2024)
- [Substitution-based Semantic Change Detection using Contextual Embeddings](https://mlsanity.com/paper/2309.02403/) (2023)
- [Tracking Semantic Change in Slovene: A Novel Dataset and Optimal Transport-Based Distance](https://mlsanity.com/paper/2402.16596/) (2024)
- [Deep-change at AXOLOTL-24: Orchestrating WSD and WSI Models for Semantic Change Modeling](https://mlsanity.com/paper/2408.05184/) (2024)
- [Dynamics of Meaning: Towards the Evaluation of Diachronic Semantic Change in Sinhala](https://mlsanity.com/paper/2609.08609/) (2026)

## Abstract (arXiv)

This paper describes the winning contribution to SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection (Subtask 2) handed in by team UG Student Intern. We present an ensemble model that makes predictions based on context-free and context-dependent word representations. The key findings are that (1) context-free word representations are a powerful and robust baseline, (2) a sentence classification objective can be used to obtain useful context-dependent word representations, and (3) combining those representations increases performance on some datasets while decreasing performance on others.