# CALE : Concept-Aligned Embeddings for Both Within-Lemma and Inter-Lemma Sense Differentiation

arXiv: https://arxiv.org/abs/2508.04494 · HTML: https://mlsanity.com/paper/2508.04494/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection](https://mlsanity.com/paper/2007.11464/) (2020)
- [SenseBERT: Driving Some Sense into BERT](https://mlsanity.com/paper/1908.05646/) (2019)
- [Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity](https://mlsanity.com/paper/2003.04866/) (2020)
- [UiO-UvA at SemEval-2020 Task 1: Contextualised Embeddings for Lexical Semantic Change Detection](https://mlsanity.com/paper/2005.00050/) (2020)
- [MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models](https://mlsanity.com/paper/2109.09237/) (2021)
- [Task Compass: Scaling Multi-task Pre-training with Task Prefix](https://mlsanity.com/paper/2210.06277/) (2022)
- [CoSimLex: A Resource for Evaluating Graded Word Similarity in Context](https://mlsanity.com/paper/1912.05320/) (2019)
- [ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality](https://mlsanity.com/paper/2110.06376/) (2021)
- [LSCDiscovery: A shared task on semantic change discovery and detection in Spanish](https://mlsanity.com/paper/2205.06691/) (2022)
- [Semantic Frame Induction using Masked Word Embeddings and Two-Step Clustering](https://mlsanity.com/paper/2105.13466/) (2021)
- [Word sense extension](https://mlsanity.com/paper/2306.05609/) (2023)
- [To Word Senses and Beyond: Inducing Concepts with Contextualized Language Models](https://mlsanity.com/paper/2406.20054/) (2024)
- [MULTISEM at SemEval-2020 Task 3: Fine-tuning BERT for Lexical Meaning](https://mlsanity.com/paper/2007.12432/) (2020)

## Abstract (arXiv)

Lexical semantics is concerned with both the multiple senses a word can adopt in different contexts, and the semantic relations that exist between meanings of different words. To investigate them, Contextualized Language Models are a valuable tool that provides context-sensitive representations that can be used to investigate lexical meaning. Recent works like XL-LEXEME have leveraged the task of Word-in-Context to fine-tune them to get more semantically accurate representations, but Word-in-Context only compares occurrences of the same lemma, limiting the range of captured information. In this paper, we propose an extension, Concept Differentiation, to include inter-words scenarios. We provide a dataset for this task, derived from SemCor data. Then we fine-tune several representation models on this dataset. We call these models Concept-Aligned Embeddings (CALE). By challenging our models and other models on various lexical semantic tasks, we demonstrate that the proposed models provide efficient multi-purpose representations of lexical meaning that reach best performances in our experiments. We also show that CALE's fine-tuning brings valuable changes to the spatial organization of embeddings.