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

• URL: http://arxiv.org/abs/2506.06169v1
• Date: Fri, 06 Jun 2025 15:33:27 GMT
• Title: semantic-features: A User-Friendly Tool for Studying Contextual Word Embeddings in Interpretable Semantic Spaces
• Authors: Jwalanthi Ranganathan, Rohan Jha, Kanishka Misra, Kyle Mahowald,
• Abstract summary: We introduce semantic-features, an easy-to-use library for studying contextualized word embeddings of LMs.<n>We measure the contextual effect of the choice of dative construction on the semantic interpretation of utterances.<n>By applying semantic-features, we show that the contextualized word embeddings of three masked language models show the expected sensitivities.
• Score: 16.888898382945012
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Driving Context into Text-to-Text Privatization [0.0]
  textitMetric Differential Privacy enables text-to-text privatization by adding noise to the vector of a word. We demonstrate a substantial increase in classification accuracy by $6.05%$.
  arXiv  Detail & Related papers  (2023-06-02T11:33:06Z)
• A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces [11.564029462243631]
  We study semantic construal in grammatical constructions using large language models. We show that a word in subject position is interpreted as more agentive than the very same word in object position. Our method can probe the distributional meaning of syntactic constructions at a templatic level, abstracted away from specific lexemes.
  arXiv  Detail & Related papers  (2023-05-29T20:30:38Z)
• Syntax and Semantics Meet in the "Middle": Probing the Syntax-Semantics Interface of LMs Through Agentivity [68.8204255655161]
  We present the semantic notion of agentivity as a case study for probing such interactions. This suggests LMs may potentially serve as more useful tools for linguistic annotation, theory testing, and discovery.
  arXiv  Detail & Related papers  (2023-05-29T16:24:01Z)
• Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations [80.45474362071236]
  It is unclear whether the compositional semantics of sentences can be directly reflected as compositional operations in the embedding space. We propose InterSent, an end-to-end framework for learning interpretable sentence embeddings.
  arXiv  Detail & Related papers  (2023-05-24T00:44:49Z)
• Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis [3.515619810213763]
  We propose using automatically generated natural language definitions of contextualised word usages as interpretable word and word sense representations. We demonstrate how the resulting sense labels can make existing approaches to semantic change analysis more interpretable.
  arXiv  Detail & Related papers  (2023-05-19T20:36:21Z)
• SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings [4.479834103607384]
  Adding interpretability to word embeddings represents an area of active research in text representation. We present SensePOLAR, an extension of the original POLAR framework that enables word-sense aware interpretability for pre-trained contextual word embeddings.
  arXiv  Detail & Related papers  (2023-01-11T20:25:53Z)
• Textual Entailment Recognition with Semantic Features from Empirical Text Representation [60.31047947815282]
  A text entails a hypothesis if and only if the true value of the hypothesis follows the text. In this paper, we propose a novel approach to identifying the textual entailment relationship between text and hypothesis. We employ an element-wise Manhattan distance vector-based feature that can identify the semantic entailment relationship between the text-hypothesis pair.
  arXiv  Detail & Related papers  (2022-10-18T10:03:51Z)
• Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks [58.87961226278285]
  We propose a self-supervised approach to model lexical semantic change. We show that our method can be used for the detection of semantic change with any alignment method. We illustrate the utility of our techniques using experimental results on three different datasets.
  arXiv  Detail & Related papers  (2021-01-30T18:59:43Z)
• Unsupervised Distillation of Syntactic Information from Contextualized Word Representations [62.230491683411536]
  We tackle the task of unsupervised disentanglement between semantics and structure in neural language representations. To this end, we automatically generate groups of sentences which are structurally similar but semantically different. We demonstrate that our transformation clusters vectors in space by structural properties, rather than by lexical semantics.
  arXiv  Detail & Related papers  (2020-10-11T15:13:18Z)
• A Comparative Study on Structural and Semantic Properties of Sentence Embeddings [77.34726150561087]
  We propose a set of experiments using a widely-used large-scale data set for relation extraction. We show that different embedding spaces have different degrees of strength for the structural and semantic properties. These results provide useful information for developing embedding-based relation extraction methods.
  arXiv  Detail & Related papers  (2020-09-23T15:45:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.