LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yile, Shen, Zhanyu, Huang, Hui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912378879213568
author Wang, Yile
Shen, Zhanyu
Huang, Hui
author_facet Wang, Yile
Shen, Zhanyu
Huang, Hui
contents Semantic text representation is a fundamental task in the field of natural language processing. Existing text embedding (e.g., SimCSE and LLM2Vec) have demonstrated excellent performance, but the values of each dimension are difficult to trace and interpret. Bag-of-words, as classic sparse interpretable embeddings, suffers from poor performance. Recently, Benara et al. (2024) propose interpretable text embeddings using large language models, which forms "0/1" embeddings based on responses to a series of questions. These interpretable text embeddings are typically high-dimensional (larger than 10,000). In this work, we propose Low-dimensional (lower than 500) Dense and Interpretable text embeddings with Relative representations (LDIR). The numerical values of its dimensions indicate semantic relatedness to different anchor texts through farthest point sampling, offering both semantic representation as well as a certain level of traceability and interpretability. We validate LDIR on multiple semantic textual similarity, retrieval, and clustering tasks. Extensive experimental results show that LDIR performs close to the black-box baseline models and outperforms the interpretable embeddings baselines with much fewer dimensions. Code is available at https://github.com/szu-tera/LDIR.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10354
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations
Wang, Yile
Shen, Zhanyu
Huang, Hui
Computation and Language
Semantic text representation is a fundamental task in the field of natural language processing. Existing text embedding (e.g., SimCSE and LLM2Vec) have demonstrated excellent performance, but the values of each dimension are difficult to trace and interpret. Bag-of-words, as classic sparse interpretable embeddings, suffers from poor performance. Recently, Benara et al. (2024) propose interpretable text embeddings using large language models, which forms "0/1" embeddings based on responses to a series of questions. These interpretable text embeddings are typically high-dimensional (larger than 10,000). In this work, we propose Low-dimensional (lower than 500) Dense and Interpretable text embeddings with Relative representations (LDIR). The numerical values of its dimensions indicate semantic relatedness to different anchor texts through farthest point sampling, offering both semantic representation as well as a certain level of traceability and interpretability. We validate LDIR on multiple semantic textual similarity, retrieval, and clustering tasks. Extensive experimental results show that LDIR performs close to the black-box baseline models and outperforms the interpretable embeddings baselines with much fewer dimensions. Code is available at https://github.com/szu-tera/LDIR.
title LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations
topic Computation and Language
url https://arxiv.org/abs/2505.10354