Jul 2026· The 2026 International Conference on Optical Communication and Intelligent Algorithms (OCIA 2026)· Vol 14301, pp. 143010B - 143010B-8· 0 citations· 16 references
Engineering
TL;DR
A lightweight yet highly accurate sequence labeling algorithm that combines domain-adaptive contextual embeddings with a BiLSTM-CRF framework augmented by an attention mechanism to address the pressing challenge of accurately identifying lexical and syntactic ambiguities in heterogeneous academic corpora is introduced.
Abstract
Contextual word embeddings and deep learning architectures have demonstrated remarkable potential in advancing ambiguity detection for academic English texts. This study introduces a lightweight yet highly accurate sequence labeling algorithm that combines domain-adaptive contextual embeddings with a BiLSTM-CRF framework augmented by an attention mechanism. This study addresses the pressing challenge of accurately identifying lexical and syntactic ambiguities in heterogeneous academic corpora. Traditional rule-based and static embedding methods have been unable to meet this requirement. To ensure language diversity and robustness, the corpus from ACL Anthology and IEEE Xplore was comprehensively preprocessed and fine-tuned in a specific field. Experimental evaluation shows that the proposed model achieves state-of-the-art accuracy while maintaining the computational efficiency required for real-time applications. The proposed model significantly outperforms the traditional baselines in terms of both recall and precision. Using model quantization techniques can greatly reduce inference time and detection performance. Contextual representation and deep sequence modeling can achieve reliable and scalable ambiguity detection in challenging academic fields. This suggests that this can provide concrete solutions for machine translation and academic search systems.
Current advances in neural network models have improved state-of-the-art performance in natural language processing tasks such as named-entity recognition, sentiment analysis, and machine translation. In particular, neural language models are applied to encode information in word embeddings. These approaches are generally trained on large corpora using semi-supervised learning. Word embeddings encode the syntactic and semantic properties of words as dense vectors. In agglutinative languages such as Turkish, Finnish, and Hungarian, word-embedding construction is challenging because extensive suffixation and polysemy can cause information loss. To overcome these limitations, character n-grams are often preferred for embedding representations. Nevertheless, character n-grams do not guarantee the capture of information in long word sequences. In this study, a method that partitions word sequences according to frequent patterns within a given context is proposed for training a neural language model. In this respect, likelihood- and ranking-based inference are combined with n-gram and syllable partitioning for word-embedding generation from a text corpus. The proposed approach provides a language-agnostic, context-sensitive segmentation mechanism that can complement language processing methods such as lemmatization, morphological analysis, and stemming. For embedding generation, the SkipGram and FastText models are used, and the effects of word partitioning are evaluated using analogy, named-entity recognition, POS tagging, sentiment analysis, and morphological disambiguation datasets for Turkish. The results indicate task-dependent and generally limited improvements over traditional token-based word-embedding extraction. In particular, skip n-gram partitioning produces a substantial improvement over partitioning based on frequent-ngrams, sentencepiece-bpe, sentence-unigram and morfessor. No consistent relationship was observed across tasks between performance and either graph density or the average number of distinct n-grams per sentence.
The rapid growth of textual data has made text classification a fundamental task in Natural Language Processing (NLP). However, real-world texts often exhibit semantic ambiguity, limited contextual information, and unclear category boundaries, which hinder conventional models from learning discriminative representations. To address these challenges, this paper proposes an Ambiguity-Aware Semantic Fusion Framework (AAK-LASFNet) for robust text classification.The proposed model constructs dual-view semantic representations by combining local contextual features extracted by a TextRCNN encoder with global semantic knowledge obtained from a large language model. An ambiguity estimation module is introduced to model semantic uncertainty, improving the model’s ability to handle ambiguous samples. Meanwhile, a label-aware attention mechanism and a keyword enhancement module are employed to strengthen category-related semantic cues. To further capture complex interactions between local and global representations, a high-order semantic fusion strategy is developed. In addition, a semantic consistency loss is imposed to align different semantic views and enhance representation stability.Extensive experiments on four benchmark datasets demonstrate that the proposed framework consistently outperforms strong baselines in terms of Accuracy, highlighting its effectiveness in alleviating semantic ambiguity in text classification.
Peijun Xie· Poster Volume 0007 The 2026...· 0 citations
A robust preprocessing pipeline incorporating Google Translation, spaCy-based NER with hyphenated-word normalization, and a future-event-aware fallback logic is proposed, achieving a 40 percent reduction in inference latency and closing the linguistic generalization gap left by previous works.
Rishabh Kumar, Aditya Kumar· Journal of Frontiers in Mult...· 0 citations
This paper proposes a general optimization framework that combines a vocabulary pruning method with a targeted fine-tuning protocol for MNMT models, and reduces the vocabulary size from over 128,000 to approximately 10,000 tokens, enabling a 60% memory saving without any loss in performance.
Ahmed Amine Aliane, N. Semmar, H. Aliane· 0 citations
A robust WSD model that integrates a bidirectional long shortterm memory network (BiLSTM) with an attention mechanism, specifically designed for Chinese patent texts is proposed, providing reliable support for knowledge mining and intelligent text processing in technical domains.
L. X. Gao, T. Dong, M. H. Yang· Advanced Electromagnetics· 0 citations
This paper proposes an alignment-aware multi-granularity tagging framework. First, this method uses a cross-lingual pre-trained model to encode source and target language contexts jointly while explicitly modeling-level bilingual correspondences via a learnable soft alignment layer. Second, a gated local enhancement module is introduced to dynamically fuse n-gram-level surface features on top of the Transformer high-level representation, preserving fine-grained error signals that are easily smoothed by attention mechanisms. Finally, a label-aware focus loss function is designed to alleviate the extreme imbalance between positive and negative samples. This function supports joint prediction of four types of fine-grained error labels. Results showed that on the large-scale benchmark of WMT QE Shared Task 2023, covering six language pairs, alignment-aware multi-granularity tagging achieved 78.6% in Micro-F1, 72.3% in Macro-F1, and improved Recall@Rare to 62.3%, especially excelling in low-frequency error types and significantly outperforming the baseline model.
Bijuan Wang, Lingli Zhu, Hongli Wen· International Journal of Inf...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
