Papers with sentence embedding models

14 papers
AugCSE: Contrastive Sentence Embedding with Diverse Augmentations (2022.aacl-main)

Copied to clipboard

Challenge: Similar work has shown that a single augmentation can be used to learn a robust generalpurpose representation with contrastive learning.
Approach: They propose a unified framework to utilize diverse sets of data augmentations to achieve a better, general-purpose sentence embedding model.
Outcome: The proposed framework achieves state-of-the-art results on downstream transfer tasks and performs competitively on semantic textual similarity tasks, using only unsupervised data.
Capturing the Relationship Between Sentence Triplets for LLM and Human-Generated Texts to Enhance Sentence Embeddings (2024.findings-eacl)

Copied to clipboard

Challenge: Recent advances in building sentence embedding models have centered on replacing traditional human-generated text datasets with those generated by LLMs.
Approach: They propose a loss function that incorporates Positive-Negative sample Augmentation within the contrastive learning objective to enhance sentence embeddings using both human and LLM-generated datasets.
Outcome: The proposed model mitigates the sentence anisotropy problem in Wikipedia corpus and improves Spearman’s correlation in standard Semantic Textual Similarity (STS) tasks (+1.47% compared to CLHAIF).
Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer (2020.aacl-main)

Copied to clipboard

Challenge: Fine-tuning (FT) pre-trained sentence embedding models on small datasets has been shown to have limitations.
Approach: They propose to combine embeddings from a pre-trained model with a simple sentence embeddable model.
Outcome: The proposed approach outperforms FT on small datasets with negligible computational overhead.
Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding (2024.eacl-long)

Copied to clipboard

Challenge: Recent trends in learning monolingual and multilingual sentence embeddings are based on contrastive learning (CL) among an anchor, one positive and multiple negative instances.
Approach: They propose to leverage multiple positives to improve learning of multilingual sentence embeddings by using an anchor, one positive, and multiple negative instances.
Outcome: The proposed approach improves retrieval, semantic similarity, and classification performance on unseen languages.
Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models (2021.naacl-main)

Copied to clipboard

Challenge: Pre-trained language models have been successful on a wide range of NLP tasks . however, contextual representations from pre-trated models contain entangled semantic and syntactic information.
Approach: They propose a semantic sentence embedding model that disentangles semantics and syntax from pre-trained models.
Outcome: The proposed model outperforms state-of-the-art models on unsupervised semantic similarity tasks.
PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs (2026.eacl-long)

Copied to clipboard

Challenge: Existing evaluations of sentence embedding models rely on static tests like the Massive Text Embedding Benchmark (MTEB) repeated tuning on a fixed suite can inflate reported performance and obscure real-world robustness.
Approach: They propose a dynamic protocol that generates meaning-preserving paraphrases at evaluation time and aggregates results across multiple runs.
Outcome: The proposed protocol generates meaning-preserving paraphrases at evaluation time and aggregates results across multiple runs.
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing contrastive methods for learning universal sentence embeddings have limitations due to their over-parameterization and poor performance under domain shift settings.
Approach: They propose to integrate an Energy-based Hinge loss to enhance the pairwise discriminative power of contrastive learning for sentence embeddings by combining PLMs with energy-based learning.
Outcome: Empirical results show that the proposed method improves on seven standard semantic textual similarity tasks and a domain-shifted STS task.
Syntax-guided Neural Module Distillation to Probe Compositionality in Sentence Embeddings (2023.eacl-main)

Copied to clipboard

Challenge: Past work on sentence embedding models faces issues determining the causal impact of implicit syntax representations.
Approach: They construct a neural module net based on a transformer model and train it end-to-end to approximate the sentence’s embedding.
Outcome: The proposed model captures whether syntax is a strong model of its compositional ability.
Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing sentence embeddings models are monolingual, and only for English . a new method allows to create multilingual versions from monolingual models .
Approach: They propose a method to extend existing sentence embedding models to new languages . they use a translated sentence to generate sentence embeds for the source language .
Outcome: The proposed method improves accuracy for multilingual setups and languages.
TR-MTEB: A Comprehensive Benchmark and Embedding Model Suite for Turkish Sentence Representations (2025.findings-emnlp)

Copied to clipboard

Challenge: TR-MTEB is the first large-scale, task-diverse benchmark for sentence embedding models for Turkish.
Approach: a new benchmark evaluates sentence embedding models for Turkish . TR-MTEB covers six core tasks and 26 high-quality datasets .
Outcome: The TR-MTEB benchmark covers six core tasks and includes 26 high-quality datasets . the models achieve competitive performance across most tasks and significantly improve on baseline models.
MultiClaimNet: A Massively Multilingual Dataset of Fact-Checked Claim Clusters (2025.findings-emnlp)

Copied to clipboard

Challenge: a growing number of unverified claims and expanding size of fact-checked databases require alternative, more efficient solutions.
Approach: They propose to group fact-checked claims into multilingual clusters to improve claim retrieval and validation.
Outcome: The proposed approach reduces redundancy by grouping claims into clusters . the proposed dataset contains 85.3K fact-checked claims written in 78 languages .
StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding (2023.emnlp-main)

Copied to clipboard

Challenge: Analogy-making between narratives is crucial for human reasoning . despite its importance, there has been limited research on story analogies .
Approach: They construct a large-scale story-level analogy corpus with 24K story pairs . they find that the tasks are incredibly difficult for large language models such as ChatGPT .
Outcome: The proposed corpus contains 24K story pairs from diverse domains with human annotations on two similarities from the extended Structure-Mapping Theory.
Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to learn sentence embeddings do not capture the semantic similarity of sentences.
Approach: They propose a framework that integrates compositional sentence operations into the embedding space and optimizes operator networks and a bottleneck encoder-decoder model to produce meaningful and interpretable sentence embeddables.
Outcome: The proposed framework improves the interpretability of sentence embeddings on four textual generation tasks while maintaining strong performance on traditional semantic similarity tasks.
When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits (2025.findings-acl)

Copied to clipboard

Challenge: Existing claims-matching systems that use sentence embedding models are not robust to edits as users interact with claims online.
Approach: They propose a perturbation framework that generates valid and natural claim variations and evaluate different mitigation approaches to improve their findings.
Outcome: The proposed framework evaluates embedding models in a multi-stage retrieval pipeline and identifies the effectiveness of mitigation approaches.

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