Use BiLSTM with Attention Mechanism to Optimize the Accuracy of Word Meaning Correspondence in Technical Texts

Semantic Analysis and Translation Optimization of English Sentences Based on Long Short-Term Memory (LSTM) Networks

Accurate semantic analysis and translation of complex English sentences are essential for intelligent information interaction and multilingual communication in modern digital systems, including semantic communication frameworks and electromagnetic-enabled intelligent networks. To address semantic omissions and logical inconsistencies caused by long-distance dependencies and referential ambiguity, this study proposes a GAT-BiLSTM fusion model that integrates dependency syntactic analysis with graph attention mechanisms and bidirectional long short-term memory networks. A lightweight semantic graph is first constructed to capture structural dependencies, after which graph representations are adaptively fused with contextual features through a gating mechanism to obtain unified semantic embeddings. During decoding, semantic gating and multi-head attention collaboratively enhance contextual coherence and semantic alignment. Experimental results demonstrate that the proposed model achieves a BLEU score exceeding 68.7, subject and action semantic matching scores of 0.88 and 0.84, respectively, and a syntactic structure retention rate of 72% for complex sentences. The proposed framework effectively improves translation fidelity and semantic consistency while exhibiting strong robustness for structurally complex inputs. Furthermore, the semantic modeling strategy provides methodological support for multilingual information processing, semantic communication, and intelligent human– machine interaction in electromagnetic wave propagation and wireless communication environments.

Leveraging LLMs to Automatically Construct WordNets as Bilingual Resources

Context-Sensitive N-Gram Word Partitioning for Improving the Quality of Turkish Word Embeddings

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.

Scaling Unsupervised Word Alignment to Documents via Structural Constraints

CTFAlign is introduced, a lightweight, training-free approach for document-level word alignment that applies a coarse-to-fine refinement strategy that restricts the alignment search space to semantically similar regions and introduces MDPAlign, a simpler alternative that constrains alignments by position with a main diagonal prior.

Sahara Tokenizers at MWE-2026 PARSEME 2.0 Subtask 1: Combining Contextual Embeddings with Structural Decoding for Multi-Word Expression Detection

Alation studies reveal a strong synergy between POS features and CRF decoding, with the combined approach yielding the best single-model performance, and ensembling models trained with different objectives improves both overall F1 score and discontinuous MWE scores, demonstrating the importance of training diversity for capturing non-adjacent syntactic patterns.

Neural Turing Machines for efficient natural language summarization: architecture, optimization, and performance analysis

Abstractive text summarization remains a fundamental challenge in Natural Language Processing (NLP), particularly for long documents that require models to preserve long-range dependencies and maintain semantic coherence. Although Transformer-based architectures have achieved strong summarization performance, their full self-attention mechanism scales quadratically with sequence length and often requires input truncation in long-context applications. This study presents a Neural Turing Machine (NTM)-based framework for abstractive text summarization. The proposed architecture combines a two-layer Bidirectional Long Short-Term Memory (BiLSTM) controller with an addressable external memory bank. Differentiable read and write operations decouple contextual storage from recurrent computation, enabling the persistent retrieval of salient information across extended input sequences. Detailed preprocessing, implementation, training, decoding, and evaluation settings are provided to support reproducibility. The framework was evaluated on the CNN/Daily Mail benchmark and compared with LSTM, Transformer, and BART baselines, as well as published high-performing systems, including PEGASUS, SimCLS, and BRIO. Ablation studies, learning-rate sensitivity analysis, long-context evaluation, inference-time scaling, statistical testing, qualitative error analysis, and memory-access visualization were also conducted. The proposed NTM model achieved ROUGE-1, ROUGE-2, ROUGE-L, and BLEU scores of 47.8, 23.5, 44.6, and 20.1, respectively. Under the controlled experimental protocol, it outperformed the evaluated LSTM, Transformer, and BART baselines. Comparisons with published results indicate that the model is competitive with recent high-performing summarization systems. The additional analyses demonstrate that the external memory mechanism improves contextual retention and summarization stability, particularly for longer input sequences, while exhibiting favorable inference-time scaling behavior. These findings demonstrate that integrating an addressable external memory with a BiLSTM controller offers an effective approach to abstractive summarization, particularly when processing long documents. The proposed framework provides competitive summarization performance while reducing dependence on computationally expensive full self-attention. The results highlight the potential of external-memory architectures as a scalable and stable alternative for long-context text summarization.