What does this research mean for the field?

The Negation-Aligned Similarity (NAS) Scorer significantly improves sentence similarity estimation by effectively modeling negation-induced semantic shifts, achieving an F1-score of 0.97. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.CHALLENGES_CONSENSUS.

What question did this study set out to answer?

To improve sentence similarity scoring by addressing the effects of negation in text using a hybrid deep learning framework.

March 3, 2026Open Access

Computation of sentence similarity score through hybrid deep learning with a special focus on negation sentence

Key Points

To improve sentence similarity scoring by addressing the effects of negation in text using a hybrid deep learning framework.
Developed a hybrid semantic similarity framework with a focus on negation.
Integrated multi-embedding fusion techniques including BERT and DistilBERT.
Utilized BiLSTM for contextual encoding to capture sequence dependencies.
Created a custom Negation-Sentence-Similarity Dataset with verified pairs.
Achieved an F1-score of 0.97 after scale normalization.
Significantly outperformed existing transformer-based baseline models on the STS Benchmark dataset.
Enhanced similarity estimation by effectively addressing semantic shifts caused by negation.

Abstract

Accurate sentence similarity estimation is a fundamental requirement in Automated Evaluation Systems (AES), where reliable semantic alignment directly impacts grading fairness and consistency. While transformer-based Sentence Similarity Tools (SSTs) perform effectively on non-negated text, they exhibit notable limitations in modeling the semantic distortions introduced by negation. To overcome this challenge, this paper proposes a novel Negation-Aligned Similarity (NAS) Scorer within a hybrid semantic similarity framework, specifically designed for negation-aware semantic modeling. The proposed method integrates multi-embedding fusion using BERT, SBERT, RoBERTa, DistilBERT, and Word2Vec, followed by BiLSTM-based contextual encoding to capture the sequential dependencies. A custom Negation-Sentence-Similarity Dataset (NSSD) comprising 8575 human-verified sentence pairs across four technical domains is curated. Experimental evaluations on the STS Benchmark dataset demonstrate that the proposed NAS Scorer achieves a F1-score of 0.97 after scale normalization, significantly outperforming strong transformer-based baselines. By explicitly addressing negation-induced semantic shifts, the proposed framework enables richer and more reliable similarity estimation, making it well-suited for deployment in real-world AES.

Bookmark

View Full Paper