# semantic-features: A User-Friendly Tool for Studying Contextual Word Embeddings in Interpretable Semantic Spaces

arXiv: https://arxiv.org/abs/2506.06169 · HTML: https://mlsanity.com/paper/2506.06169/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models](https://mlsanity.com/paper/2203.13112/) (2022)
- [Investigating representations of verb bias in neural language models](https://mlsanity.com/paper/2010.02375/) (2020)
- [Do Language Models Exhibit Human-like Structural Priming Effects?](https://mlsanity.com/paper/2406.04847/) (2024)
- [A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces](https://mlsanity.com/paper/2305.18598/) (2023)
- [A systematic framework for generating novel experimental hypotheses from language models](https://mlsanity.com/paper/2408.05086/) (2024)
- [Do Language Models Learn Position-Role Mappings?](https://mlsanity.com/paper/2202.03611/) (2022)

## Built on by (most cited first, 1 of 1)

- [Meaning-infused grammar: Gradient Acceptability Shapes the Geometric Representations of Constructions in LLMs](https://mlsanity.com/paper/2507.22286/) (2025)

## Abstract (arXiv)

We introduce semantic-features, an extensible, easy-to-use library based on Chronis et al. (2023) for studying contextualized word embeddings of LMs by projecting them into interpretable spaces. We apply this tool in an experiment where we measure the contextual effect of the choice of dative construction (prepositional or double object) on the semantic interpretation of utterances (Bresnan, 2007). Specifically, we test whether "London" in "I sent London the letter." is more likely to be interpreted as an animate referent (e.g., as the name of a person) than in "I sent the letter to London." To this end, we devise a dataset of 450 sentence pairs, one in each dative construction, with recipients being ambiguous with respect to person-hood vs. place-hood. By applying semantic-features, we show that the contextualized word embeddings of three masked language models show the expected sensitivities. This leaves us optimistic about the usefulness of our tool.