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

Overview

1. Nocancer.ai, San Francisco, CA, United States
2. Department of Computer Science, University of Colorado, Colorado Springs, CO, United States

Abstract

Introduction: 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.

Methods: 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.

Results: 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.

Discussion: 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.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• github.com/abisee/cnn-dailymail, at github.com; found in “Data availability statement”

Data availability statement

Publicly available datasets were analyzed in this study. This data can be found here: https://github.com/abisee/cnn-dailymail.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 3 authors, 6 keywords, 11 references.

Cite

This paper

Katti, K. R., Katti, K. R., & Islam, A. (2026). Neural Turing Machines for efficient natural language summarization: architecture, optimization, and performance analysis. Frontiers in artificial intelligence, 9, 1889866. https://doi.org/10.3389/frai.2026.1889866

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3390/e24111514 [code]

QAScore-An Unsupervised Unreferenced Metric for the Question Generation Evaluation.

Journal: Entropy (Basel, Switzerland)

In common: 2 references

[2] doi:10.1038/s41598-024-84530-w [code]

Brain-model neural similarity reveals abstractive summarization performance.

Journal: Scientific reports

In common: cognitive, 1 reference

[3] doi:10.3389/frai.2022.774752 [code]

Affordance embeddings for situated language understanding.

Journal: Frontiers in artificial intelligence

In common: cognitive, 1 reference

[4] doi:10.1155/2022/6856567 [code]

Heavyweight Statistical Alignment to Guide Neural Translation.

Journal: Computational intelligence and neuroscience

In common: cognitive, 1 reference

[5] doi:10.1021/jacsau.5c00289 [code]

HiCLR: Knowledge-Induced Hierarchical Contrastive Learning with Retrosynthesis Prediction Yields a Reaction Foundation Model.

Journal: JACS Au

In common: 1 reference

[6] doi:10.3389/fninf.2023.1067095

A systematic comparison of deep learning methods for EEG time series analysis.

Journal: Frontiers in neuroinformatics

In common: 1 reference

[7] doi:10.1016/j.scog.2026.100443 [code]

From thought to language: Comparing schizophrenia spectrum disorders and Wernicke's aphasia with machine learning and LLMs.

Journal: Schizophrenia research. Cognition

In common: cognitive, 1 reference

[8] doi:10.1002/hbm.70379

From Speech Semantics to Brain Activity-Timescales Are Key in Their Information Transfer.

Journal: Human brain mapping

In common: cognitive, 1 reference

[9] doi:10.1038/s43588-025-00863-0 [code]

Increasing alignment of large language models with language processing in the human brain.

Journal: Nature computational science

In common: cognitive, 1 reference

[10] doi:10.1162/nol.a.12

Challenges and Methods in Annotating Natural Speech for Neurolinguistic Research.

Journal: Neurobiology of language (Cambridge, Mass.)

In common: cognitive, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.