Challenge: Existing text embeddings with high dimensions are difficult to trace and interpret.
Approach: They propose low-dimensional and interpretable text embeddings with relative representations that encode semantic meanings in a vector space where similar texts are close together in the representation space.
Outcome: The proposed embeddings outperform existing models on multiple tasks with fewer dimensions and are lowdimensional and dense while maintaining interpretability.

Similar Papers

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval (2025.emnlp-main)

Copied to clipboard

Challenge: Existing sparse retrieval methods suffer from a lack of interpretability . we propose a new interpretability framework that decomposes dense embeddings into distinct, interpretable latent concepts.
Approach: They propose a new interpretability framework that leveragesSparse Autoencoders to decompose uninterpretable dense embeddings fromDPR models into distinct, interpretable latent concepts.
Outcome: The proposed interpretability framework achieves high index-space and computational efficiency while maintaining robust performance across vocabulary and semantic mismatches.
Word2Sense: Sparse Interpretable Word Embeddings (P19-1)

Copied to clipboard

Challenge: Word2Sense embeddings are interpretable, but they are sparse and fast to compute . a unitary rotation can be applied to many of these embeddables retaining their utility for computational tasks while changing the values of individual coordinates.
Approach: They propose an unsupervised method to generate Word2Sense word embeddings that are interpretable.
Outcome: The proposed method compares well with other unsupervised word embeddings on NLP tasks.
Which Evaluations Uncover Sense Representations that Actually Make Sense? (2020.lrec-1)

Copied to clipboard

Challenge: Existing sense representations fail for human-centric tasks like inspecting a language’s sense inventory.
Approach: They propose a coherence evaluation for sense embeddings and a model optimized for finding interpretable sense representations that are more coherent than existing sense embeds.
Outcome: The proposed model is more coherent than existing sense embeddings and offers comparable word similarities with multisense representations while learning more distinguishable, interpretable senses.
Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval (2021.emnlp-main)

Copied to clipboard

Challenge: Recent approaches to information retrieval (IR) and natural language processing (NLP) use contextual language models, which can improve both synonymy and polysemy problems associated with words.
Approach: They propose an ultra-high dimensional representation scheme equipped with directly controllable sparsity and a bucketing method where embeddings from multiple layers of BERT are selected/merged to represent diverse linguistic aspects.
Outcome: The proposed representation scheme outperforms sparse models with MS MARCO and TREC CAR, and shows that it is highly efficient for storage and search.
Evaluating Embedding APIs for Information Retrieval (2023.acl-industry)

Copied to clipboard

Challenge: a growing number of language models are limiting their access to the community . we evaluate existing APIs for domain generalization and multilingual retrieval .
Approach: They evaluate semantic embedding APIs in retrieval scenarios to assess their capabilities . they use BEIR and MIRACL to re-rank BM25 results using the APIs .
Outcome: The proposed model is based on semantic embedding APIs that build vector representations of a given text.
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.
Enhancing Lexicon-Based Text Embeddings with Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks.
Approach: They introduce the first lexicon-based embeddings that consolidates the vocabulary space through token embeddation clustering to handle the issue of token redundancy in LLM vocabularies.
Outcome: The proposed model outperforms dense embeddings on the Massive Text Embedding Benchmark (MTEB) it also supports efficient dimension pruning without any specialized objectives like Matryoshka Representation Learning.
SMEC:Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models generate high-dimensional embeddings that capture rich semantic and syntactic information.
Approach: They propose a training framework to reduce dimensionality and complexity of large language models.
Outcome: Experiments on image, text, and multimodal datasets show that the proposed training framework reduces dimensionality while maintaining performance.
The Devil is in the Details: Evaluating Limitations of Transformer-based Methods for Granular Tasks (2020.coling-main)

Copied to clipboard

Challenge: Contextual embeddings have shown state-of-the-art performance for various tasks such as question answering, sentiment analysis, and textual similarity.
Approach: They propose to integrate transformer-based neural language models into their models to achieve relative improvements of up to 36% on granular tasks.
Outcome: The proposed model outperforms baselines for more granular tasks while outperforming TF-IDF for more complex tasks.
Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings? (2023.findings-eacl)

Copied to clipboard

Challenge: obtaining document embeddings at document level is challenging due to computational requirements and lack of appropriate data.
Approach: They compare methods to produce document-level representations from sentences based on LASER, LaBSE, and Sentence BERT pre-trained multilingual models.
Outcome: The proposed methods produce document-level representations from sentences in 8 languages . the results show that a clever combination of sentence embeddings is usually better than encoding the full document as a single unit.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations