| Challenge: | Existing research into semantic textual similarity has focused on word embeddings . little attention has been devoted to similarity measures between word embeds - a new study shows . |
| Approach: | They show that cosine similarity is essentially equivalent to the Pearson correlation coefficient for all common word vectors. |
| Outcome: | The proposed model outperforms the existing model on word-level and sentence-level similarity benchmarks. |
Similar Papers
A Rank-Based Similarity Metric for Word Embeddings (P18-2)
Copied to clipboard
| Challenge: | Word Embeddings have become a standard for word representations, with vector cosine being the only similarity metric. |
| Approach: | They propose to use rank-based similarity estimation metrics to measure word similarity . they find WE outperforms vector cosine in the recent outlier detection task . |
| Outcome: | The proposed rank-based measure outperforms vector cosine in the recent outlier detection task. |
Text Similarity Estimation Based on Word Embeddings and Matrix Norms for Targeted Marketing (N19-1)
Copied to clipboard
| Challenge: | Existing methods to estimate document similarity based on word embeddings are mediocre . a recent study compared word and sentence embedded documents to a similarity estimate using matrix norms. |
| Approach: | They propose to combine word embeddings with matrix norms to obtain a similarity estimate. |
| Outcome: | The proposed method produces superior results for most of the investigated matrix norms compared to the classical cosine measure and several other similarity estimates. |
Correlations between Word Vector Sets (D19-1)
Copied to clipboard
| Challenge: | Similarity measures based on word embeddings are easily competing with deep learning and expert-engineered systems on unsupervised semantic textual similarity tasks. |
| Approach: | They propose a new approach to measure word embeddings using pooling operations and correlation coefficients instead of pooling . they also propose centered kernel alignment as a natural generalisation of squared cosine similarity for sets of word vectors. |
| Outcome: | The proposed approach outperforms most recent methods while being much faster and trivial to implement. |
Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words (2022.acl-short)
Copied to clipboard
| Challenge: | We find that word similarities estimated by cosine over contextual embeddings are understated and trace this effect to training data frequency. |
| Approach: | They propose to use cosine similarity to estimate word similarities in contextual embeddings to trace this effect to training data frequency. |
| Outcome: | The proposed model underestimates similarity between frequent and low frequency words even after controlling for polysemy and other factors. |
Estimating Mutual Information Between Dense Word Embeddings (2020.acl-main)
Copied to clipboard
| Challenge: | Word embedding-based similarity measures are among the top-performing methods on unsupervised semantic textual similarity tasks. |
| Approach: | They propose a word embedding similarity measure that is a viable alternative to correlations and gives an excellent signal that correlates well with human judgements of similarity. |
| Outcome: | The proposed model outperforms existing state-of-the-art methods on hard NLP tasks. |
On the Correlation of Word Embedding Evaluation Metrics (2020.lrec-1)
Copied to clipboard
| Challenge: | Word embeddings are geometrical representations of word paradigmatics and syntagmatics. |
| Approach: | They propose to investigate evaluation metrics on various datasets to find correlations . they propose a fast solution to select the best word embeddings among many others . |
| Outcome: | The proposed method could be used to select the best word embeddings among many others. |
Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on cosine similarity focus on the angle or correlation coefficient, but this study proposes a novel interpretation of the term word similarity. |
| Approach: | They propose a method for selecting statistically significant axes by deriving the probability distributions that govern each component and the product of components. |
| Outcome: | The proposed interpretation of cosine similarity is demonstrated through intuitive numerical examples and thorough numerical experiments. |
Rethinking Word Similarity: Semantic Similarity through Classification Confusion (2025.naacl-long)
Copied to clipboard
| Challenge: | Word similarity measures cannot capture context-dependent, asymmetrical, polysemous nature of semantic similarity. |
| Approach: | They propose a new measure of similarity that reframes semantic similarity in terms of feature-based classification confusion. |
| Outcome: | The proposed model is comparable to cosine similarity in matching human similarity judgments across several datasets and can measure similarity using predetermined features of interest. |
Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual Similarity (2023.acl-short)
Copied to clipboard
| Challenge: | Semantic Textual Similarity (STS) measures the degree to which the underlying semantics of paired sentences are equivalent. |
| Approach: | They propose a token-level matching inference algorithm which can be applied on top of any language model to improve its performance on STS task. |
| Outcome: | The proposed method improves the performance of almost all language models, with up to 12.7% gain in Spearman’s correlation. |
Interpretable Text Embeddings and Text Similarity Explanation: A Survey (2025.emnlp-main)
Copied to clipboard
| Challenge: | Text embeddings are a fundamental component in many NLP tasks, but their interpretation and explanation remain challenging. |
| Approach: | They propose a framework for interpretable text embeddings and text similarity explanation . they characterize the main ideas, approaches, and trade-offs and discuss lessons learned . |
| Outcome: | The proposed methods are compared with existing models and compare them with existing ones. |